Pascal Fua
EPFL IC IINFCOM CVLAB
BC 310 (Bâtiment BC)
Station 14
1015 Lausanne
Web site: Web site: https://cvlab.epfl.ch/
+41 21 693 66 47
EPFL
>
IC
>
IC-SIN
>
SIN-ENS
Web site: Web site: https://sin.epfl.ch
Fields of expertise
Computer Vision, Biomedical Imaging, and Machine Learning
Biography
Pascal Fua received an engineering degree from Ecole Polytechnique, Paris, in 1984 and the Ph.D. degree in Computer Science from the University of Orsay in 1989. He then worked at SRI International and INRIA Sophia-Antipolis as a Computer Scientist. He joined EPFL in 1996 where he is now a Professor in the School of Computer and Communication Science and heads the Computer Vision Laboratory.His research interests include shape modeling and motion recovery from images, analysis of microscopy images, and machine learning. He has (co)authored over 300 publications in refereed journals and conferences. He is an IEEE Fellow and has been an Associate Editor of IEEE journal Transactions for Pattern Analysis and Machine Intelligence. He often serves as program committee member, area chair, and program chair of major vision conferences and has cofounded three spinoff companies (Pix4D, PlayfulVision, and NeuralConcept).
Current Work
The research activities of the Computer Vision Laboratory focus on shape and motion recovery from images, object and people detection and tracking in video sequences, and analysis of brain microscopy image-stacks. CVLab also provides undergraduate and graduate teaching and performs technology transfer to both established and start up companies.Pascal Fua
Publications
Infoscience publications
All since 1996
2025
Harnessing deep learning to detect bronchiolitis obliterans syndrome from chest CT
COMMUNICATIONS MEDICINE. 2025. DOI : 10.1038/s43856-025-00732-x.Efficient anatomical labeling of pulmonary tree structures via deep point-graph representation-based implicit fields
Medical image analysis. 2025. DOI : 10.1016/j.media.2024.103367.MetaCap: Meta-learning Priors from Multi-view Imagery for Sparse-View Human Performance Capture and Rendering
2025. 18th European Conference on Computer Vision, Milan, Italy, 2024-09-29 - 2024-10-04. p. 341 - 361. DOI : 10.1007/978-3-031-72952-2_20.Improving Human Pose & Shape Estimation with Explicit and Implicit Priors
Lausanne, EPFL, 2025. DOI : 10.5075/epfl-thesis-10577.2024
Reconstruction of Manipulated Garment with Guided Deformation Prior
2024. 38th Annual Conference on Neural Information Processing Systems, Vancouver Convention Center, 2024-12-10 - 2024-12-15.No Identity, no problem: Motion through detection for people tracking
Transactions on Machine Learning Research. 2024.CLOAF: CoLlisiOn-Aware Human Flow
2024. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition CVPR 2024, Seattle, WA, USA, 2024-06-17 - 2024-06-21. p. 1176 - 1185. DOI : 10.1109/CVPR52733.2024.00118.Enabling Uncertainty Estimation in Iterative Neural Networks
2024. International Conference on Machine Learning, Vienna, July 21-27, 2024.Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes
Transactions on Machine Learning Research. 2024. DOI : 10.48550/arXiv.2402.02736.Aggregating Spatial and Photometric Context for Photometric Stereo
Lausanne, EPFL, 2024. DOI : 10.5075/epfl-thesis-9806.DiffAirfoil: An Efficient Novel Airfoil Sampler Based on Latent Space Diffusion Model for Aerodynamic Shape Optimization
2024. AIAA AVIATION Forum, Las Vegas, NV, USA, July 29–August 2, 2024.Generating Anatomically Accurate Heart Structures via Neural Implicit Fields
2024. International Conference on Medical Image Computing and Computer-Assisted Intervention, MARRAKESH, MOROCCO, 2024-10-06 - 2024-10-10.DeepMesh: Differentiable Iso-Surface Extraction
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024.A Closed-Form Pairwise Solution to Local Non-Rigid Structure-from-Motion
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024. DOI : 10.1109/TPAMI.2024.3383316.Incorporating Projective Geometry into Deep Learning
Lausanne, EPFL, 2024. DOI : 10.5075/epfl-thesis-10538.Detecting Road Obstacles by Erasing Them
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024. DOI : 10.1109/TPAMI.2023.3335152.MedShapeNet - a large-scale dataset of 3D medical shapes for computer vision
Biomedizinische Technik. Biomedical engineering. 2024. DOI : 10.1515/bmt-2024-0396.DeepGeo: Deep Geometric Mapping for Automated and Effective Parameterization in Aerodynamic Shape Optimization
2024.2023
Learning for Multi-View Tracking
2023Latent Representation of Computational Fluid Dynamics Meshes and Application to Airfoil Aerodynamics
Aiaa Journal. 2023. DOI : 10.2514/1.J062533.State of the Art in Dense Monocular Non-Rigid 3D Reconstruction
Computer Graphics Forum. 2023. DOI : 10.1111/cgf.14774.BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets
Nature Methods. 2023. DOI : 10.1038/s41592-023-01848-5.Perspective Aware Road Obstacle Detection
Ieee Robotics And Automation Letters. 2023. DOI : 10.1109/LRA.2023.3245410.Geodesic Convolutional Neural Network Characterization of Macro-Porous Latent Thermal Energy Storage
ASME Journal of Heat and Mass Transfer. 2023. DOI : 10.1115/1.4056663.Informing Neural Networks with Simplified Physics for Better Flow Prediction
2023Detecting Anomalies and Obstacles in Road Scenes
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-8972.Improving Object Detection under Domain Shifts
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-9805.Multi-view Tracking Using Weakly Supervised Human Motion Prediction
2023. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), Waikoloa, Hawaii, USA, January 3-7, 2023. DOI : 10.1109/WACV56688.2023.0016.Tracking Adaptation to Improve SuperPoint for 3D Reconstruction in Endoscopy
2023. 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023), Vancouver, BC, Canada, October 8–12, 2023. p. 583 - 593. DOI : 10.1007/978-3-031-43907-0_56.GECCO: Geometrically-Conditioned Point Diffusion Models
2023. IEEE/CVF International Conference on Computer Vision (ICCV), Paris, FRANCE, OCT 02-06, 2023. p. 2128 - 2138. DOI : 10.1109/ICCV51070.2023.00203.Dense Image-based Predictions for Comics Analysis
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-10212.Latent Representation of CFD Meshes and Application to Airfoil Aerodynamics
2023A method and system for enforcing smoothness constraints on surface meshes from a graph convolutional neural network
US2023169732 . 2023.Deep Learning for 3D Surface Modelling and Reconstruction
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-10386.LightDepth: Single-View Depth Self-Supervision from Illumination Decline
2023. International Conference on Computer Vision (ICCV), Paris, October 3-5, 2023. DOI : 10.1109/ICCV51070.2023.01945.LightNeuS: Neural Surface Reconstruction in Endoscopy using Illumination Decline
2023. 26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Vancouver, Canadda, October 8-12, 2023. p. 502 - 512. DOI : 10.1007/978-3-031-43999-5_48.Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning
2023. AIAA Aviation Forum 2023, San Diego, CA, USA, June 12-16, 2023. DOI : 10.2514/6.2023-3471.Automated Human Motion Analysis and Synthesis
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-8976.Multi-view Tracking UsingWeakly Supervised Human Motion Prediction
2023. 23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, Jan 03-07, 2023. p. 1582 - 1592. DOI : 10.1109/WACV56688.2023.00163.DrapeNet: Garment Generation and Self-Supervised Draping
2023. The 2023 IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), Vancouver, Canada, 2023-06-18 - 2023-06-22. p. 1451 - 1460. DOI : 10.1109/CVPR52729.2023.00146.Topologically Better Delineation of Curvilinear Structures
Lausanne, EPFL, 2023. DOI : 10.5075/epfl-thesis-9749.ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns
2023. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), New Orleans, Louisiana, USA, December 10-16, 2023. DOI : 10.48550/arXiv.2305.14100.Geometrically-Conditioned Point Diffusion Models
2023. International Conference on Computer Vision (ICCV), Paris.Two-level Data Augmentation for Calibrated Multi-view Detection
2023. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), Waikoloa, Hawaii, USA, January 3-7, 2023. p. 128 - 136. DOI : 10.1109/WACV56688.2023.00021.2022
Overcoming the Domain Gap in Neural Action Representations
International Journal Of Computer Vision. 2022. DOI : 10.1007/s11263-022-01713-6.Self-supervised Segmentation via Background Inpainting
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022. DOI : 10.1109/TPAMI.2021.3123902.3D Pose Based Feedback For Physical Exercises
2022. 16th Asian Conference on Computer Vision (ACCV 2022), Macau, China, December 4-8, 2022. p. 1316 - 1332. DOI : 10.1007/978-3-031-26316-3_12.Adversarial Parametric Pose Prior
2022. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, Louisiana, USA, June 18-24, 2022. p. 10987 - 10995. DOI : 10.1109/CVPR52688.2022.01072.Weakly Supervised Volumetric Image Segmentation with Deformed Templates
2022. 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022), Singapore, September 18-22, 2022. p. 422 - 432. DOI : 10.1007/978-3-031-16443-9_41.Long Term Motion Prediction Using Keyposes
2022. International Conference on 3D Vision (3DV), Prague, Czech Republic, September 12-15, 2022. p. 12 - 21. DOI : 10.1109/3DV57658.2022.00014.On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation
2022. 10th International Conference on 3D Vision 2022 (3DV), Prague, Czechia, September 12-15, 2022. p. 577 - 586. DOI : 10.1109/3DV57658.2022.00068.Generating LOD3 building models from structure-from-motion and semantic segmentation
Automation In Construction. 2022. DOI : 10.1016/j.autcon.2022.104430.TOPO-Loss for continuity-preserving crack detection using deep learning
Construction And Building Materials. 2022. DOI : 10.1016/j.conbuildmat.2022.128264.Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate
IEEE Transactions on Medical Imaging. 2022. DOI : 10.1109/TMI.2022.3193072.ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging
2022. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). p. 15840 - 15850. DOI : 10.1109/CVPR52688.2022.01540.3D reconstruction of curvilinear structures with stereo matching deep convolutional neural networks
Ultramicroscopy. 2022. DOI : 10.1016/j.ultramic.2021.113460.Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysis
2022. 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Singapore, SINGAPORE, Sep 18-22, 2022. p. 503 - 513. DOI : 10.1007/978-3-031-16440-8_48.Learning to Represent and Reconstruct 3D Deformable Objects
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-7974.MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks
2022. European Conference on Computer Vision (ECCV 2022), Tel-Aviv, Israel, October 23-27, 2022. p. 576 - 592. DOI : 10.1007/978-3-031-20062-5_33.Synthesis and Analysis of 3D shapes with Geometric Deep Learning in Computer-Aided Engineering
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-8798.Understanding Deep Neural Networks using Adversarial Attacks
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-9259.Learning to Align Sequential Actions in the Wild
2022. CVPR 2022 : IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, United States, Jun 18-24, 2022. p. 2171 - 2181. DOI : 10.1109/CVPR52688.2022.00222.Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2022. DOI : 10.1109/TPAMI.2022.3215307.Persistent Homology with Improved Locality Information for more Effective Delineation
2022Using Animal Motion Capture to Learn Neural Representations
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-9124.Object Priors for Volumetric Image Segmentation
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-8853.DIG: Draping Implicit Garment over the Human Body
2022. 16th Asian Conference on Computer Vision (ACCV 2022), Macau SAR, China, December 4-8, 2022. p. 344 - 359. DOI : 10.1007/978-3-031-26319-4_21.Enforcing Connectivity of 3D Linear Structures Using Their 2D Projections
2022. 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Singapore, SINGAPORE, Sep 18-22, 2022. p. 591 - 601. DOI : 10.1007/978-3-031-16443-9_57.Counting People by Estimating People Flows
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022. DOI : 10.1109/TPAMI.2021.3102690.Leveraging Self-Supervision for Cross-Domain Crowd Counting
2022. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, Jun 18-24, 2022. p. 5331 - 5342. DOI : 10.1109/CVPR52688.2022.00527.Learning to Simulate Realistic LiDARs
2022. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Kyoto, Japan, October 23-27, 2022. p. 8173 - 8180. DOI : 10.1109/IROS47612.2022.9981120.HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulation
2022. International Conference on 3D Vision, Prague, Czechia, September 12-15, 2022. DOI : 10.1109/3DV57658.2022.00072.Promoting Connectivity of Network-Like Structures by Enforcing Region Separation
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022. DOI : 10.1109/TPAMI.2021.3074366.Encoder-Decoder Models for Human Segmentation and Motion Analysis
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-8036.Improving the Training of Compact Neural Networks for Visual Recognition
Lausanne, EPFL, 2022. DOI : 10.5075/epfl-thesis-9061.2021
Human Detection and Segmentation via Multi-view Consensus
2021. ICCV 2021 International Conference on Computer Vision, Montreal, Canada (online), October 11-17, 2021. p. 2835 - 2844. DOI : 10.1109/ICCV48922.2021.00285.Defect segmentation for multi-illumination quality control systems
Machine Vision and Applications. 2021. DOI : 10.1007/s00138-021-01244-z.Structure-aware Multi-view 3D Reconstruction of Dislocations in TEM with Message Passing Neural Networks
Joint Meeting of Dreiländertagung & Multinational Congress on Microscopy (Microscopy Conference 2021), Digital, August 22-26, 2021.Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems
Ieee Transactions On Pattern Analysis And Machine Intelligence. 2021. DOI : 10.1109/TPAMI.2020.2978812.Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases
2021. 18th IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada (online), October 11-17, 2021. p. 10438 - 10447. DOI : 10.1109/ICCV48922.2021.01029.LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals
Nature Methods. 2021. DOI : 10.1038/s41592-021-01226-z.Wide-Depth-Range 6D Object Pose Estimation in Space
2021. Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, June 19-25, 2021. p. 15870 - 15879. DOI : 10.1109/CVPR46437.2021.01561.Deep Active Surface Models
2021. Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, June 21-25, 2021. p. 11652 - 11661. DOI : 10.1109/CVPR46437.2021.01148.Masksembles for Uncertainty Estimation
2021. Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, June 19-25, 2021. p. 13539 - 13548. DOI : 10.1109/CVPR46437.2021.01333.Matching Seqlets: An Unsupervised Approach for Locality Preserving Sequence Matching
IEEE Transactions On Pattern Analysis And Machine Intelligence (PAMI). 2021. DOI : 10.1109/TPAMI.2019.2934052.Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches
2021. International Conference on Computer Vision (ICCV), Virtual, October 11-17, 2021. p. 13003 - 13012. DOI : 10.1109/ICCV48922.2021.01278.Human-Centered Scene Understanding via Crowd Counting
Lausanne, EPFL, 2021. DOI : 10.5075/epfl-thesis-8979.Robust Differentiable SVD
IEEE Transactions On Pattern Analysis And Machine Intelligence (PAMI). 2021. DOI : 10.1109/TPAMI.2021.3072422.From Human-Designed Convolutional Neural Networks Towards Robust Neural Architecture Search
Lausanne, EPFL, 2021. DOI : 10.5075/epfl-thesis-8035.SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation
2021. Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track, virtual, December 6-14, 2021.Image Matching Across Wide Baselines: From Paper to Practice
International Journal Of Computer Vision. 2021. DOI : 10.1007/s11263-020-01385-0.Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo
2021. 9th International Conference on 3D Vision (3DV), ELECTR NETWORK, Dec 01-03, 2021. p. 394 - 402. DOI : 10.1109/3DV53792.2021.00049.Motion Prediction Using Temporal Inception Module
2021. Asian Conference on Computer Vision (ACCV), Kyoto, Japan, December, 2020. p. 651 - 665. DOI : 10.1007/978-3-030-69532-3_39.2020
Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
2020. Conference on Computer Vision and Pattern Recognition (CVPR). p. 13155 - 13165. DOI : 10.1109/CVPR42600.2020.01317.TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation
2020. European Conference on Computer Vision (ECCV), [Online event], August 23-28, 2020.XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera
Acm Transactions On Graphics (TOG). 2020. DOI : 10.1145/3386569.3392410.Single-Stage 6D Object Pose Estimation
2020. Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, June 16 - 18, 2020. p. 2927 - 2936. DOI : 10.1109/CVPR42600.2020.00300.Shape Reconstruction by Learning Differentiable Surface Representations
2020. Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, June 14-16, 2020. p. 4715 - 4724. DOI : 10.1109/CVPR42600.2020.00477.Joint Segmentation and Path Classification of Curvilinear Structures
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2020. DOI : 10.1109/TPAMI.2019.2921327.ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
2020. Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA, June 14-19, 2020. p. 100 - 109. DOI : 10.1109/CVPR42600.2020.00018.MeshSDF: Differentiable Iso-Surface Extraction
2020. Conference on Neural Information Processing Systems (NeurIPS), [Virtual event], December, 2020.DISK: learning local features with policy gradient
2020. Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada (online), December 6-12, 2020.Real-time camera pose estimation for sports fields
Machine Vision and Applications (MVA). 2020. DOI : 10.1007/s00138-020-01064-7.Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures
Medical Image Analysis. 2020. DOI : 10.1016/j.media.2019.101590.Learning and leveraging shared domain semantics to counteract visual domain shifts
Lausanne, EPFL, 2020. DOI : 10.5075/epfl-thesis-10000.Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images
IEEE Transactions on Medical Imaging. 2020. DOI : 10.1109/TMI.2019.2946462.Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images
2020. European Conference on Computer Vision (ECCV 2020), [Virtual conference], August 23-28, 2020.Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data
2020. International Conference On Medical Image Computing & Computer Assisted Intervention (MICCAI), Lima, Peru, 4-8 OCTOBER 2020.Better Patch Stitching for Parametric Surface Reconstruction
2020. 8th International Conference on 3D Vision (3DV), ELECTR NETWORK, Nov 25-28, 2020. p. 593 - 602. DOI : 10.1109/3DV50981.2020.00069.Domain-Adaptive Multibranch Networks
2020. International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, April 26-30, 2020.Local Non-Rigid Structure-from-Motion from Locally Diffeomorphic Mappings
2020. Computer Vision and Pattern Recognition (CVPR), Seattle, USA, June 16-18, 2020. p. 2056 - 2064. DOI : 10.1109/CVPR42600.2020.00213.UCLID-Net: Single View Reconstruction in Object Space
2020. 34th Conference on Neural Information Processing Systems, Virtual, December 6-12, 2020.2019
Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation
2019. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China, November 4-8, 2019. p. 244 - 249. DOI : 10.1109/IROS40897.2019.8967852.Detecting the Unexpected via Image Resynthesis
2019. IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, SOUTH KOREA, Oct 27-Nov 02, 2019. p. 2152 - 2161. DOI : 10.1109/ICCV.2019.00224.Probabilistic Atlases to Enforce Topological Constraints
2019. 22rd International Conference On Medical Image Computing & Computer Assisted Intervention, Shenzhen, China, 2019-10-13. DOI : 10.1007/978-3-030-32239-7_25.DeepFly3D, a deep learning-based approach for 3D limb and appendage tracking in tethered, adult Drosophila
eLife. 2019. DOI : 10.7554/eLife.48571.Are Existing Monocular Computer Vision-Based 3D Motion Capture Approaches Ready for Deployment? A Methodological Study on the Example of Alpine Skiing
Sensors. 2019. DOI : 10.3390/s19194323.Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking
2019. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, Jun 16-20, 2019. p. 4634 - 4643. DOI : 10.1109/CVPR.2019.00477.Aerodynamic shape optimization via surrogate modelling with convolutional neural networks
2019Neural Scene Decomposition for Multi-Person Motion Capture
2019. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, Jun 16-20, 2019. p. 7695 - 7705. DOI : 10.1109/CVPR.2019.00789.Context-Aware Crowd Counting
2019. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, June 16-20, 2019. p. 5094 - 5103. DOI : 10.1109/CVPR.2019.00524.Segmentation-driven 6D Object Pose Estimation
2019. Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, USA, June 16-20, 2019. p. 3380 - 3389. DOI : 10.1109/CVPR.2019.00350.Mo(2)Cap(2): Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera
IEEE Transactions On Visualization And Computer Graphics. 2019. DOI : 10.1109/TVCG.2019.2898650.Geometry in active learning for binary and multi-class image segmentation
Computer Vision And Image Understanding (CVIU). 2019. DOI : 10.1016/j.cviu.2019.01.007.A Performance Evaluation of Local Features for Image-Based 3D Reconstruction
IEEE Transactions on Image Processing. 2019. DOI : 10.1109/TIP.2019.2909640.Training Algorithms for Multiple Object Tracking
Lausanne, EPFL, 2019. DOI : 10.5075/epfl-thesis-9203.Shape optimisation of technical devices via gradient descent using convolutional neural network proxies
US11768983 ; US2021157962 ; EP3679495 ; CN111295657 ; WO2019048085 . 2019.GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping
2019. IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, SOUTH KOREA, Oct 27-Nov 02, 2019. p. 8738 - 8747. DOI : 10.1109/ICCV.2019.00883.Backpropagation-Friendly Eigendecomposition
2019. Conference on Neural Information Processing Systems (NeurIPS), Vancouver, CANADA, Dec 08-14, 2019.What Face and Body Shapes Can Tell Us About Height
2019. IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, SOUTH KOREA, Oct 27-Nov 02, 2019. p. 1819 - 1827. DOI : 10.1109/ICCVW.2019.00226.Gravity as a Reference for Estimating a Person's Height from Video
2019. IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, SOUTH KOREA, Oct 27-Nov 02, 2019. p. 8568 - 8576. DOI : 10.1109/ICCV.2019.00866.Beyond Cartesian Representations for Local Descriptors
2019. IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, SOUTH KOREA, Oct 27-Nov 02, 2019. p. 253 - 262. DOI : 10.1109/ICCV.2019.00034.Learning Approach to Delineation of Curvilinear Structures in 2D and 3D Images
Lausanne, EPFL, 2019. DOI : 10.5075/epfl-thesis-9301.Learning to Reduce Annotation Load
Lausanne, EPFL, 2019. DOI : 10.5075/epfl-thesis-9074.2018
Real-Time Seamless Single Shot 6D Object Pose Prediction
2018. Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018. p. 292 - 301. DOI : 10.1109/CVPR.2018.00038.Modeling Facial Geometry using Compositional VAEs
2018. Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, June 18-22, 2018. p. 3877 - 3886. DOI : 10.1109/CVPR.2018.00408.Learning to Reconstruct Texture-less Deformable Surfaces from a Single View
2018. International Conference on 3D Vision, Verona, Italy, September 5-8, 2018.Learning Latent Representations of 3D Human Pose with Deep Neural Networks
International Journal of Computer Vision. 2018. DOI : 10.1007/s11263-018-1066-6.Mean-Field methods for Structured Deep-Learning in Computer Vision
Lausanne, EPFL, 2018. DOI : 10.5075/epfl-thesis-8677.Beyond the Pixel-Wise Loss for Topology-Aware Delineation
2018. Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, June 18-22, 2018. p. 3136 - 3145. DOI : 10.1109/CVPR.2018.00331.A Domain-Adaptive Two-Stream U-Net For Electron Microscopy Image Segmentation
2018. International Symposium on Biomedical Imaging (ISBI), Washington, DC, Apr 04-07, 2018. p. 400 - 404. DOI : 10.1109/ISBI.2018.8363602.Learning Monocular 3D Human Pose Estimation from Multi-view Images
2018. Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, Jun 18-23, 2018. p. 8437 - 8446. DOI : 10.1109/CVPR.2018.00880.Variational Methods for Human Modeling
Lausanne, EPFL, 2018. DOI : 10.5075/epfl-thesis-8680.Scale-Adaptive Superpixels
2018. Color and Imaging Conference (CIC26), Vancouver, Canada, November 12-16, 2018. p. 1 - 6(6). DOI : 10.2352.Geodesic Convolutional Shape Optimization
2018. International Conference on Machine Learning (ICML), Stockholm, Sweden, July, 2018. p. 472 - 481.Learning to Find Good Correspondences
2018. Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, Jun 18-23, 2018. p. 2666 - 2674. DOI : 10.1109/CVPR.2018.00282.Learning Robust Features and Latent Representations for Single View 3D Pose Estimation of Humans and Objects
Lausanne, EPFL, 2018. DOI : 10.5075/epfl-thesis-8753.Method, system, and device for learned invariant feature transform for computer images
US10552709 ; US2018096224 . 2018.Every Smile is Unique: Landmark-Guided Diverse Smile Generation
2018. 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, Jun 18-23, 2018. p. 7083 - 7092. DOI : 10.1109/CVPR.2018.00740.Beyond Sharing Weights for Deep Domain Adaptation
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018. DOI : 10.1109/TPAMI.2018.2814042.Unsupervised Geometry-Aware Representation Learning for 3D Human Pose Estimation
2018. European Conference on Computer Vision (ECCV). p. 765 - 782. DOI : 10.1007/978-3-030-01249-6_46.A Domain-Adaptive Two-Stream U-Net for Electron Microscopy Image Segmentation
2018. International Symposium of Biomedical Imaging (ISBI), Washington DC, USA, April 4-7, 2018. p. 400 - 404. DOI : 10.1109/ISBI.2018.8363602.Residual Parameter Transfer for Deep Domain Adaptation
2018. Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, June 18-22, 2018. p. 4339 - 4348. DOI : 10.1109/CVPR.2018.00456.Learning to Find Good Correspondences
2018. Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, June 18-22, 2018. p. 2666 - 2674. DOI : 10.1109/CVPR.2018.00282.Learning to Segment 3D Linear Structures Using Only 2D Annotations
2018. MICCAI, Granada, Spain, September 16-20, 2018. p. 283 - 291. DOI : 10.1007/978-3-030-00934-2_32.LF-Net: Learning Local Features from Images
2018. Neural Information Processing Systems (NIPS), Montréal Canada.Learning to Reconstruct Texture-less Deformable Surfaces from a Single View
2018. 6th International Conference on 3D Vision (3DV), Verona, ITALY, Sep 05-08, 2018. p. 606 - 615. DOI : 10.1109/3DV.2018.00075.Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses
2018. European Conference on Computer Vision, Munich, Germany, September 8-14, 2018. p. 768 - 783. DOI : 10.1007/978-3-030-01228-1_47.2017
Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
2017. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, USA, July 21-26, 2017. p. 3425 - 3434. DOI : 10.1109/Cvpr.2017.365.Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences
Transactions on Medical Imaging (TMI). 2017. DOI : 10.1109/Tmi.2016.2640859.Active Learning and Proofreading for Delineation of Curvilinear Structures
2017. MICCAI, Quebec City, Canada, September 10-14, 2017. p. 165 - 173. DOI : 10.1007/978-3-319-66185-8_19.Imposing Hard Constraints on Deep Networks: Promises and Limitations
2017. CVPR Workshop on Negative Results in Computer Vision, Hawaii, HI, 2017.Geometric Graph Matching Using Monte Carlo Tree Search
Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2017. DOI : 10.1109/Tpami.2016.2636200.Multi-Modal Mean-Fields via Cardinality-Based Clamping
2017. Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, Hawaii, USA, July 21-26, 2017. p. 4303 - 4312. DOI : 10.1109/Cvpr.2017.458.Detecting Flying Objects using a Single Moving Camera
Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2017. DOI : 10.1109/TPAMI.2016.2564408.Flight Dynamics-based Recovery of a UAV Trajectory using Ground Cameras
2017. Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, July, 2017. p. 2482 - 2491. DOI : 10.1109/Cvpr.2017.266.Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery
2017. International Conference on Medical Image Computing and Computer-Assisted Intervention (MCCAI), Quebec, Canada.Method, System and Device for Direct Prediction of 3D Body Poses from Motion Compensated Sequence
US2017316578 . 2017.Reconstructing Evolving Tree Structures in Time Lapse Sequences by Enforcing Time-Consistency
Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2017. DOI : 10.1109/TPAMI.2017.2680444.Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
2017. International Conference on Computer Vision (ICCV). p. 3961 - 3970. DOI : 10.1109/ICCV.2017.425.Learning Lightprobes for Mixed Reality Illumination
2017. International Symposium on Mixed and Augmented Reality (ISMAR), Nantes, France, October 9–13, 2017.Vision-based detection of aircrafts and UAVs
Lausanne, EPFL, 2017. DOI : 10.5075/epfl-thesis-7589.Stereo-vision three-dimensional reconstruction of curvilinear structures imaged with a TEM
Ultramicroscopy. 2017. DOI : 10.1016/j.ultramic.2017.08.010.Computer Vision Techniques Applied to the Reconstruction of the 3-D Structure of Dislocations
2017. Microscopy & Microanalysis, St Louis, MO, USA, 2017. p. 102 - 103. DOI : 10.1017/S1431927617001192.Three-dimensional electron imaging and reconstruction of dislocations from a single acquisition
2017. Microscopy Conference, Lausanne, Switzerland.Tilt-less 3-D electron imaging and reconstruction of complex curvilinear structures
Scientific Reports. 2017. DOI : 10.1038/s41598-017-07537-6.2016
Vision-Based Unmanned Aerial Vehicle Detection and Tracking for Sense and Avoid Systems
2016. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea, October 9-14, 2016. p. 1556 - 1561. DOI : 10.1109/IROS.2016.7759252.Measuring the accuracy of softball impact simulations
Sports Engineering. 2016. DOI : 10.1007/s12283-016-0210-1.Automated Reconstruction of Evolving Curvilinear Tree Structures
Lausanne, EPFL, 2016. DOI : 10.5075/epfl-thesis-6930.What Players do with the Ball: A Physically Constrained Interaction Modeling
2016. International Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Jun 26 - Jul 1 2016. p. 972 - 981. DOI : 10.1109/CVPR.2016.111.Computer vision profiling of neurite outgrowth dynamics reveals spatio-temporal modularity of Rho GTPase signaling
Journal of Cell Biology. 2016. DOI : 10.1083/jcb.201506018.Tracking Interacting Objects Using Intertwined Flows
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016. DOI : 10.1109/Tpami.2015.2513406.Structured Prediction of 3D Human Pose with Deep Neural Networks
2016. British Machine Vision Conference (BMVC), York, UK, September 19-22, 2016. p. 130.1 - 130.11. DOI : 10.5244/C.30.130.Active Learning for Delineation of Curvilinear Structures
2016. Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 2016. p. 5231 - 5239. DOI : 10.1109/CVPR.2016.565.Multiscale Centerline Extraction Based on Regression and Projection onto the Set of Elongated Structures
Lausanne, EPFL, 2016. DOI : 10.5075/epfl-thesis-7241.Towards Scalable Segmentation of 3D Image Stacks
Lausanne, EPFL, 2016. DOI : 10.5075/epfl-thesis-6937.Robust 3D Object Pose Estimation and Tracking from Monocular Images in Industrial Environments
Lausanne, EPFL, 2016. DOI : 10.5075/epfl-thesis-7282.Template-based Monocular 3-D Shape Reconstruction And Tracking Using Laplacian Meshes
Lausanne, EPFL, 2016. DOI : 10.5075/epfl-thesis-6891.Reconstructing Curvilinear Networks using Path Classifiers and Integer Programming
IEEE Transactions On Pattern Analysis And Machine Intelligence (PAMI). 2016. DOI : 10.1109/Tpami.2016.2519025.Scalable Unsupervised Domain Adaptation for Electron Microscopy
2016. MICCAI 2016, Athens, Greece, October 17-21, 2016. p. 326 - 334. DOI : 10.1007/978-3-319-46723-8_38.Globally Optimal Cell Tracking using Integer Programming
2016Analyzing Volleyball Match Data from the 2014 World Championships Using Machine Learning Techniques
2016. Conference on Knowledge Discovery and Data Mining, San Francisco, CA, August, 2016. p. 627 - 634. DOI : 10.1145/2939672.2939725.Simultaneous segmentation and anatomical labeling of the cerebral vasculature
Medical Image Analysis. 2016. DOI : 10.1016/j.media.2016.03.006.Principled Parallel Mean-Field Inference for Discrete Random Fields
2016. Computer Vision and Pattern Recognition (CVPR), Las Vegas. p. 5848 - 5857. DOI : 10.1109/CVPR.2016.630.Learning to Match Aerial Images with Deep Attentive Architectures
2016. Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, June 27-30, 2016. p. 3539 - 3547. DOI : 10.1109/CVPR.2016.385.Direct Prediction of 3D Body Poses from Motion Compensated Sequences
2016. Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, June 26-July 1, 2016. p. 991 - 1000. DOI : 10.1109/CVPR.2016.113.Template-based Monocular 3D Shape Recovery using Laplacian Meshes
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016. DOI : 10.1109/Tpami.2015.2435739.Learning to Assign Orientations to Feature Points
2016. Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada, USA, June 26-July 1, 2016. p. 107 - 116. DOI : 10.1109/CVPR.2016.19.Parsing human skeletons in an operating room
Machine Vision and Applications. 2016. DOI : 10.1007/s00138-016-0792-4.Multiscale Centerline Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016. DOI : 10.1109/Tpami.2015.2462363.Do We Need Binary Features for 3D Reconstruction?
2016. Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, June, 2016. p. 1126 - 1135. DOI : 10.1109/Cvprw.2016.144.LIFT: Learned Invariant Feature Transform
2016. European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands, October 8-16, 2016. p. 467 - 483. DOI : 10.1007/978-3-319-46466-4_28.Three-dimensional electron imaging of dislocations from a single sample tilt
2016. The 16th European Microscopy Congress 2016, Lyon, France, 28 August - 2 September, 2016. DOI : 10.1002/9783527808465.2015
Tracking Interacting Objects in Image Sequences
Lausanne, EPFL, 2015. DOI : 10.5075/epfl-thesis-6632.Dense image registration and deformable surface reconstruction in presence of occlusions and minimal texture
2015. International Conference on Computer Vision (ICCV), Santiago, Chile, December 13-16, 2015. p. 2273 - 2281. DOI : 10.1109/ICCV.2015.262.On Rendering Synthetic Images for Training an Object Detector
Computer Vision and Image Understanding. 2015. DOI : 10.1016/j.cviu.2014.12.006.Learning Separable Filters
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2015. DOI : 10.1109/Tpami.2014.2343229.Localizing Polygonal Objects in Man-Made Environments
Lausanne, EPFL, 2015. DOI : 10.5075/epfl-thesis-6622.Modeling Brain Circuitry over a Wide Range of Scales
Frontiers in Neuroanatomy. 2015. DOI : 10.3389/fnana.2015.00042.Introducing Geometry in Active Learning for Image Segmentation
2015. international conference in Computer Vision, Santiago, Chile, December 13-16, 2015. p. 2974 - 2982. DOI : 10.1109/ICCV.2015.340.Non-Rigid Graph Registration using Active Testing Search
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2015. DOI : 10.1109/TPAMI.2014.2343235.Kullback-Leibler Proximal Variational Inference
2015. Advances in Neural Information Processing Systems (NIPS), Montreal, Canada, December 9, 2015. p. 3402 - 3410.Systems and methods for tracking interacting objects
US9794525 ; US2015281655 . 2015.Detecting and Tracking Cells using Network Flow Programming
2015Probability Occupancy Maps for Occluded Depth Images
2015. Conference on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA, June 7-12, 2015. p. 2829 - 2837. DOI : 10.1109/CVPR.2015.7298900.Flying Objects Detection from a Single Moving Camera
2015. Conference on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA, June 7-12, 2015. p. 4128 - 4136. DOI : 10.1109/CVPR.2015.7299040.TILDE: A Temporally Invariant Learned DEtector
2015. Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA. p. 5279 - 5288. DOI : 10.1109/CVPR.2015.7299165.NeuroMorph: A Toolset for the Morphometric Analysis and Visualization of 3D Models Derived from Electron Microscopy Image Stacks
Neuroinformatics. 2015. DOI : 10.1007/s12021-014-9242-5.Discriminative Learning of Deep Convolutional Feature Point Descriptors
2015. International Conference on Computer Vision, Santiago, Chile, December 13-16, 2015. p. 118 - 126. DOI : 10.1109/ICCV.2015.22.Learning Structured Models for Segmentation of 2D and 3D Imagery
IEEE Transactions on Medical Imaging. 2015. DOI : 10.1109/TMI.2014.2376274.Special Section: Pose & Gesture
Computer Vision And Image Understanding. 2015. DOI : 10.1016/j.cviu.2015.10.011.Projection onto the Manifold of Elongated Structures for Accurate Extraction
2015. International Conference on Computer Vision (ICCV), Santiago, Chile, December 11-18, 2015. p. 316 - 324. DOI : 10.1109/ICCV.2015.44.Live Texturing of Augmented Reality Characters from Colored Drawings
IEEE Transactions on Visualization and Computer Graphics. 2015. DOI : 10.1109/Tvcg.2015.2459871.Domain Adaptation for Microscopy Imaging
IEEE Transactions on Medical Imaging. 2015. DOI : 10.1109/Tmi.2014.2376872.A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images
2015. International Conference on Computer Vision (ICCV), Santiago, Chile, December 13-16, 2015. p. 4391 - 4399. DOI : 10.1109/ICCV.2015.499.2014
[DEMO] Tracking Texture-less, Shiny Objects with Descriptor Fields
2014. International Symposium on Mixed and Augmented Reality (ISMAR), Munich, 2014. p. 331 - 332. DOI : 10.1109/ISMAR.2014.6948474.Dendritic tree extraction from noisy maximum intensity projection images in C-elegans
Biomedical Engineering Online. 2014. DOI : 10.1186/1475-925X-13-74.Identity-Preserving Multiple People Tracking
Lausanne, EPFL, 2014. DOI : 10.5075/epfl-thesis-6035.Multi-Commodity Network Flow for Tracking Multiple People
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2014. DOI : 10.1109/Tpami.2013.210.Tracking Interacting Objects Optimally Using Integer Programming
2014. European Conference on Computer Vision (ECCV), Zurich, Switzerland, September 6-12, 2014. p. 17 - 32. DOI : 10.1007/978-3-319-10590-1_2.Multiple Human Pose Estimation with Temporally Consistent 3D Pictorial Structures
2014. European Conference on Computer Vision, ChaLearn Looking at People Workshop, Zurich, Switzerland, September 6-12, 2014. p. 742 - 754. DOI : 10.1007/978-3-319-16178-5_52.Beyond KernelBoost
2014Fast Part-Based Classification for Instrument Detection in Minimally Invasive Surgery
2014. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Boston, Massachusetts, USA, September 14-18, 2014. p. 692 - 699. DOI : 10.1007/978-3-319-10470-6_86.Learning and Matching Binary Local Feature Descriptors
Lausanne, EPFL, 2014. DOI : 10.5075/epfl-thesis-6226.On the Relevance of Sparsity for Image Classification
Computer Vision and Image Understanding. 2014. DOI : 10.1016/j.cviu.2014.03.009.Exploiting Enclosing Membranes and Contextual Cues for Mitochondria Segmentation
2014. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Boston, Massachusetts, USA, September 2014.On Rendering Synthetic Images for Training an Object Detector
2014Better features for image categorization and segmentation
Lausanne, EPFL, 2014. DOI : 10.5075/epfl-thesis-6031.Re-Identification for Improved People Tracking
Person Re-Identification; Springer, 2014. p. 309 - 330.Caenorhabditis elegant segmentation using texture-based models for motility phenotyping
IEEE Transactions on Biomedical Engineering. 2014. DOI : 10.1109/Tbme.2014.2298612.Simultaneous Segmentation and Anatomical Labeling of the Cerebral Vasculature
2014. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Boston, Massachusetts, USA, Sep. 14-19, 2014.Real-time landing place assessment in man-made environments
Machine Vision And Applications. 2014. DOI : 10.1007/s00138-013-0560-7.Multiscale Centerline Detection by Learning a Scale-Space Distance Transform
2014. Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA, June 24-27, 2014. p. 2697 - 2704. DOI : 10.1109/CVPR.2014.351.Receptive Fields Selection for Binary Feature Description
IEEE Transactions on Image Processing. 2014. DOI : 10.1109/TIP.2014.2317981.Take your Eyes off the Ball: Improving Ball-Tracking by Focusing on Team Play
Computer Vision and Image Understanding. 2014. DOI : 10.1016/j.cviu.2013.11.010.Refining Mitochondria Segmentation in Electron Microscopy Imagery with Active Surfaces
2014. European Conference on Computer Vision (ECCV) Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment, Zurich, Switzerland, September 6-12, 2014. p. 367 - 379. DOI : 10.1007/978-3-319-16220-1_26.Reconstructing Evolving Tree Structures in Time Lapse Sequences
2014. Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, 2014. p. 3035 - 3042. DOI : 10.1109/CVPR.2014.388.Efficient scanning for em based target localization
WO2014001157 ; US8588509 . 2014.Correlative In Vivo 2-Photon Beam Scanning Electron Microscopy: 3D Analysis of Neuronal Ultrastructure
Correlative Light And Electron Microscopy II; San Diego: Elsevier Academic Press Inc, 2014. p. 339 - 361.Dense Methods for Image Alignment with an Application to 3D Tracking
2014Free-Shape Polygonal Object Localization
2014. European Conference on Computer Vision (ECCV), Zurich, Switzerland, Sep 6-12, 2014. p. 317 - 332. DOI : 10.1007/978-3-319-10599-4_21.2013
Keypoint Recognition using Random Forests and Random Ferns
Decision Forests for Computer Vision and Medical Image Analysis; Springer, 2013. p. 111 - 124.Learning Separable Filters
2013. Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, USA, June 25-27, 2013. p. 2754 - 2761. DOI : 10.1109/Cvpr.2013.355.Boosting Binary Keypoint Descriptors
2013. Computer Vision and Pattern Recognition (CVPR), Portland, USA. p. 2874 - 2881. DOI : 10.1109/Cvpr.2013.370.TPAMI CVPR Special Section
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2013. DOI : 10.1109/TPAMI.2013.208.Facial Descriptors for Identity-Preserving Multiple People Tracking
2013An Optimal Policy for Target Localization with Application to Electron Microscopy
2013. International Conference on Machine Learning (ICML), Atlanta, GA, USA, June 16-21, 2013. p. 1 - 9.Tubular Geodesics using Oriented Flux: An ITK Implementation
Insight Journal. 2013.Reconstructing Loopy Curvilinear Structures Using Integer Programming
2013. Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, USA, June, 2013. DOI : 10.1109/Cvpr.2013.238.Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets
2013. Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, USA, June 23-28, 2013. DOI : 10.1109/Cvpr.2013.259.Detection of Aircrafts on a Collision Course using Spatio-Temporal HOG
2013Multi-camera face detection and recognition applied to people tracking
2013Method and apparatus for multiple object tracking with k-shortest paths
US8615107 ; US2013177200 . 2013.Learning Context Cues for Synapse Segmentation
IEEE Transactions on Medical Imaging. 2013. DOI : 10.1109/Tmi.2013.2267747.Detecting Irregular Curvilinear Structures in Gray Scale and Color Imagery using Multi-Directional Oriented Flux
2013. International Conference on Computer Vision (ICCV), Sydney, Australia, December, 2013. p. 1553 - 1560. DOI : 10.1109/ICCV.2013.196.Tracklet-based Multi-Commodity Network Flow for Tracking Multiple People
EP2780871 ; EP2780871 ; WO2013072401 ; WO2013072401 . 2013.Stochastic Exploration of Ambiguities for Non-Rigid Shape Recovery
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2013. DOI : 10.1109/Tpami.2012.102.Automated Reconstruction of Curvilinear Networks from 2D and 3D Imagery
Lausanne, EPFL, 2013. DOI : 10.5075/epfl-thesis-5933.Fast Object Detection with Entropy-Driven Evaluation
2013. Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, USA, June 23-28, 2013. p. 3270 - 3277. DOI : 10.1109/CVPR.2013.420.Active Testing Search for Point Cloud Matching
2013. International Conference on Information Processing in Medical Imaging (IPMI), Asilomar, California, USA, June 28, 2013. p. 572 - 583. DOI : 10.1007/978-3-642-38868-2_48.Supervised Feature Learning for Curvilinear Structure Segmentation
2013. International Conference on Medical Image Computing And Computer Assisted Intervention (MICCAI), Nagoya, Japan, September 22-26, 2013. p. 526 - 533. DOI : 10.1007/978-3-642-40811-3_66.Tracking Multiple Handball Players using Multi-Commodity Network Flow for Assessing Tactical Behavior
2013. Scientific Conference Women and Handball: Scientific and Practical Approaches, Vienna, Austria, November, 2013.Non-Linear Domain Adaptation with Boosting
2013. Neural Information Processing Systems (NIPS), Lake Tahoe, Nevada, USA, December 5-8, 2013.Semi-Automated Reconstruction of Curvilinear Structures in Noisy 2D images and 3D image stacks
2013Learning Discriminative Features and Structured Models for Segmentation in Microscopy and Natural Images
Lausanne, EPFL, 2013. DOI : 10.5075/epfl-thesis-5836.Tracking Multiple Players using a Single Camera
2013KernelBoost: Supervised Learning of Image Features For Classification
2013Learning Separable Filters with Shared Parts
2013Separable Filter Learning with Tensor Decomposition
2013Flash Scanning Electron Microscopy
2013. 16th Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nagoya, Japan, September 22-26, 2013.2012
Efficient Scanning for EM Based Target Localization
2012. 15th International Conference on Medical Image Computing and Computer Assisted Intervention, Nice, France, October, 2012. p. 337 - 344. DOI : 10.1007/978-3-642-33454-2_42.Real time multi-object tracking using multiple cameras
2012Data-Driven Visual Tracking in Retinal Microsurgery
2012. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nice, France, October, 2012. p. 568 - 575. DOI : 10.1007/978-3-642-33418-4_70.Monocular 3D Reconstruction of Locally Textured Surfaces
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012. DOI : 10.1109/TPAMI.2011.196.Learning Separable Filters
2012Thick Boundaries in Binary Space and Their Influence on Nearest-Neighbor Search
Pattern Recognition Letters. 2012. DOI : 10.1016/j.patrec.2012.08.006.Worldwide Pose Estimation Using 3D Point Clouds
2012. European Conference on Computer Vision (ECCV), Florence, Italy, October, 2012. p. 15 - 29. DOI : 10.1007/978-3-642-33718-5_2.Hybrid Algorithms for the Minimum-Weight Rooted Arborescence Problem
2012. International Conference on Swarm Intelligence, Brussels, Belgium, September, 2012.On the Relevance of Sparsity for Image Classification
2012Automated Reconstruction of Tree Structures using Path Classifiers and Mixed Integer Programming
2012. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, June 16-21, 2012. p. 566 - 573. DOI : 10.1109/CVPR.2012.6247722.SLIC Superpixels Compared to State-of-the-art Superpixel Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012. DOI : 10.1109/TPAMI.2012.120.Transfer Learning by Sharing Support Vectors
2012Laplacian Meshes for Monocular 3D Shape Recovery
2012. European Conference on Computer Vision, Florence, October 2012.Structured Image Segmentation using Kernelized Features
2012. European Conference on Computer Vision, Florence, Italy, October 2012.AUTOMATIC MAPPING FROM ULTRA-LIGHT UAV IMAGERY
2012. EuroCOW 2012, Barceloa, Spain, February 8-10, 2012.LDAHash: Improved Matching with Smaller Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012. DOI : 10.1109/TPAMI.2011.103.Efficient Large Scale Multi-View Stereo for Ultra High Resolution Image Sets
Machine Vision and Applications. 2012. DOI : 10.1007/s00138-011-0346-8.Robust Non-Rigid Registration of 2D and 3D Graphs
2012. Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, June 2012. p. 996 - 1003. DOI : 10.1109/CVPR.2012.6247776.Learning Context Cues for Synapse Segmentation in EM Volumes
2012. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). p. 585 - 592. DOI : 10.1007/978-3-642-33415-3_72.Gradient Response Maps for Real-Time Detection of Textureless Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012. DOI : 10.1109/TPAMI.2011.206.BRIEF: Computing a Local Binary Descriptor Very Fast
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012. DOI : 10.1109/TPAMI.2011.222.Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks with Learned Shape Features
IEEE Transactions on Medical Imaging. 2012. DOI : 10.1109/TMI.2011.2171705.Resolving Ambiguities in Monocular 3D Reconstruction of Deformable Surfaces
Lausanne, EPFL, 2012. DOI : 10.5075/epfl-thesis-5458.A Constrained Latent Variable Model
2012. IEEE Conference on Computer Vision and Pattern Recognition, Providence, Rhode Island, USA, June 16-21, 2012. p. 2248 - 2255. DOI : 10.1109/CVPR.2012.6247934.A Real-Time Deformable Detector
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2012. DOI : 10.1109/TPAMI.2011.117.Learning to Detect Objects with Minimal Supervision
Lausanne, EPFL, 2012. DOI : 10.5075/epfl-thesis-5310.Learning Image Descriptors with the Boosting-Trick
2012. NIPS, Lake Tahoe, CA, USA, 2012.2011
Turning Augmented Reality into a media: Design exploration to build a dedicated visual language
2011. 2011 IEEE International Symposium on Mixed and Augmented Reality - Arts, Media, and Humanities, Basel, Switzerland, 26-29 October, 2011. p. 83 - 89. DOI : 10.1109/ISMAR-AMH.2011.6093661.Long Term Real Trajectory Reuse Through Region Goal Satisfaction
2011. International Conference on Motion in Games (MIG), Edinburgh, UK, November 13-15, 2011. p. 412 - 423. DOI : 10.1007/978-3-642-25090-3_35.Conditional Random Fields for Multi-Camera Object Detection
2011. International Conference on Computer Vision, Barcelona, Spain, November 6-13, 2011. p. 563 - 570. DOI : 10.1109/ICCV.2011.6126289.Filter Learning for Linear Structure Segmentation
2011Simplified Building Models Extraction From Ultra-Light UAV Imagery
2011. UAV-g 2011 - Unmanned Aerial Vehicle in Geomatics, Zürich, CH, September 14-16, 2011.Real-time vehicle tracking for driving assistance
Machine Vision and Applications. 2011. DOI : 10.1007/s00138-009-0243-6.Automated Detection and Delineation of Tree Structures in Noisy Micrographs
Lausanne, EPFL, 2011. DOI : 10.5075/epfl-thesis-5065.Spatio-Chromatic Decorrelation by Shift-Invariant Filtering
2011. IEEE CVPR Workshop on Biologically Consistent Vision, Colorado Springs, CO, USA, June 2011. DOI : 10.1109/CVPRW.2011.5981688.Learning Real-Time Perspective Patch Rectification
International Journal of Computer Vision. 2011. DOI : 10.1007/s11263-010-0379-x.Multiple Object Tracking using K-Shortest Paths Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2011. DOI : 10.1109/TPAMI.2011.21.Rotational Features Extraction for Ridge Detection
2011myCopter – Enabling Technologies for Personal Aerial Transportation Systems
2011. International HELI World Conference, Frankfurt/Main, Germany, 2011.myCopter – Enabling Technologies for Personal Aerial Transportation Systems.
2011. European Rotorcraft Forum, Vergiate/Gallarate, Italy, September 13-15, 2011.Linear Local Models for Monocular Reconstruction of Deformable Surfaces
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2011. DOI : 10.1109/TPAMI.2010.158.Automated Reconstruction of Dendritic and Axonal Trees by Global Optimization with Geometric Priors
Neuroinformatics. 2011. DOI : 10.1007/s12021-011-9122-1.The Accuracy of Automatic Photogrammetric Techniques on Ultra-light UAV Imagery
2011. UAV-g 2011 - Unmanned Aerial Vehicle in Geomatics, Zürich, CH, September 14-16, 2011.myCopter: Enabling Technologies for Personal Air Transport Systems
2011. RAeS Rotorcraft Conference: The Future Rotorcraft – Enabling Capability Through the Application of Technology, London, UK, 15-16th June 2011.Are Spatial and Global Constraints Really Necessary for Segmentation?
2011. IEEE International Conference on Computer Vision (ICCV), Barcelona. p. 9 - 16. DOI : 10.1109/ICCV.2011.6126219.Tracking Multiple People under Global Appearance Constraints
2011. International Conference on Computer Vision, Barcelona, Spain, November 6-13, 2011. p. 137 - 144. DOI : 10.1109/ICCV.2011.6126235.2010
DAISY: A Fast Descriptor for Dense Wide Baseline Stereo and Multiview Reconstruction
Lausanne, EPFL, 2010. DOI : 10.5075/epfl-thesis-4830.Daisy: An Efficient Dense Descriptor Applied to Wide Baseline Stereo
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2010. DOI : 10.1109/TPAMI.2009.77.Learning Pose Invariant and Covariant Classifiers from Image Sequences
Lausanne, EPFL, 2010. DOI : 10.5075/epfl-thesis-4746.Delineating Trees in Noisy 2D Images and 3D Image Stacks
2010. International Conference on Computer Vision and Pattern Recognition. p. 2799 - 2806. DOI : 10.1109/CVPR.2010.5540010.Large occlusion completion using normal maps
2010. Asian Conference on Computer Vision, Queenstown, New Zealand, November 8-12, 2010.Supervoxel-Based Segmentation of EM Image Stacks with Learned Shape Features
2010SLIC Superpixels
2010BRIEF: Binary Robust Independent Elementary Features
2010. 11th European Conference on Computer Vision (ECCV). p. 778 - 792. DOI : 10.1007/978-3-642-15561-1_56.L'HYDROPTERE: HOW MULTIDISCIPLINARY SCIENTIFIC RESEARCH MAY HELP BREAK THE SAILING SPEED RECORD
2010. 2nd INTERNATIONAL CONFERENCE ON INNOVATION IN HIGH PERFORMANCE SAILING YACHTS (Innov'Sail), Lorient, France, June 30 - 1st July 1st, 2010.Monocular 3D Reconstruction of Locally Textured Surfaces
2010L'Hydroptère: A story of a dream
2010. 21st HISWA International Symposium on Yacht Design and Yacht Construction, Amsterdam, The Netherlands, November 15-16, 2010.Combining Geometric and Appearance Priors for Robust Homography Estimation
2010. p. 58 - 72. DOI : 10.1007/978-3-642-15558-1_5.Pedestrian localization, tracking and behavior analysis from multiple cameras
Lausanne, EPFL, 2010. DOI : 10.5075/epfl-thesis-4629.View-Based Maps
International Journal of Robotics Research. 2010. DOI : 10.1177/0278364910370376.Pareto-optimal Dictionaries for Signatures
2010. Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, Jun 13-18, 2010. p. 3011 - 3018. DOI : 10.1109/CVPR.2010.5540050.Simultaneous Pose, Correspondence and Non-Rigid Shape
2010. Conference on Computer Vision and Pattern Recognition. p. 1189 - 1196. DOI : 10.1109/CVPR.2010.5539831.Reconstructing Geometrically Consistent Tree Structures from Noisy Images
2010. Medical Image Computing and Computer-Assisted Intervention (MICCAI), Beijing, China, September 20-24, 2010. p. 291 - 299. DOI : 10.1007/978-3-642-15705-9_36.Simultaneous Point Matching and 3D Deformable Surface Reconstruction
2010. 23rd IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, U.S.A., June 13-19, 2010. p. 1221 - 1228. DOI : 10.1109/CVPR.2010.5539827.Making Action Recognition Robust to Occlusions and Viewpoint Changes
2010. European Conference on Computer Vision, Heraklion, Greece, September, 2010. p. 635 - 648. DOI : 10.1007/978-3-642-15558-1_46.Fast Keypoint Recognition using Random Ferns
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2010. DOI : 10.1109/TPAMI.2009.23.From Canonical Poses to 3D Motion Capture Using a Single Camera
Ieee Transactions On Pattern Analysis And Machine Intelligence. 2010. DOI : 10.1109/TPAMI.2009.108.Deformable Surface 3D Reconstruction from Monocular Images
Morgan-Claypool.LDAHash: Improved matching with smaller descriptors
2010Pareto-optimal Dictionaries for Signatures
2010. Conference on Computer Vision and Pattern Recognition, June. p. 3011 - 3018. DOI : 10.1109/CVPR.2010.5540050.A Fully Automated Approach to Segmentation of Irregularly Shaped Cellular Structures in EM Images
2010. International Conference on Medical Image Computing and Computer Assisted Intervention, Beijing, September 20-24, 2010. p. 463 - 471. DOI : 10.1007/978-3-642-15745-5_57.Exploring Ambiguities for Monocular Non-Rigid Shape Estimation
2010. European Conference on Computer Vision, Heraklion, Greece, September, 2010. p. 370 - 383. DOI : 10.1007/978-3-642-15558-1_27.Least-Squares Minimization Under Constraints
2010Bridging the Gap between Detection and Tracking for 3D Human Motion Recovery
Lausanne, EPFL, 2010. DOI : 10.5075/epfl-thesis-4699.Robust, High-Speed Interest Point Matching for Real-Time Applications
Lausanne, EPFL, 2010. DOI : 10.5075/epfl-thesis-4868.Dynamic and Scalable Large Scale Image Reconstruction
2010. 23rd IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, U.S.A, June 13-19, 2010. p. 406 - 413. DOI : 10.1109/CVPR.2010.5540184.2009
Memories of the world of the mountains
Leonardo. 2009. DOI : 10.1162/leon.2009.42.4.350.Learning and recovering 3D surface deformations
Lausanne, EPFL, 2009. DOI : 10.5075/epfl-thesis-4270.Compact Signatures for High-speed Interest Point Description and Matching
2009. IEEE International Conference on Computer Vision, Kyoto, JAPAN, Sep 29-Oct 02, 2009. p. 357 - 364. DOI : 10.1109/ICCV.2009.5459272.Multiple Object Tracking using Flow Linear Programming
2009. 12th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (Winter-PETS 2009), Snowbird, Utah. DOI : 10.1109/PETS-WINTER.2009.5399488.Multiple Object Tracking using Flow Linear Programming
2009Template-Free Monocular Reconstruction of Deformable Surfaces
2009. International Conference on Computer Vision, Kyoto, September 27 - October 4, 2009.Joint Pose Estimator and Feature Learning for Object Detection
2009. IEEE International Conference on Computer Vision. p. 1373 - 1380. DOI : 10.1109/ICCV.2009.5459304.EPnP: An Accurate O(n) Solution to the PnP Problem
International Journal Of Computer Vision. 2009. DOI : 10.1007/s11263-008-0152-6.Learning Rotational Features for Filament Detection
2009. International Conference on Computer Vision and Pattern Recognition. p. 1582 - 1589. DOI : 10.1109/CVPR.2009.5206511.Capturing 3D Stretchable Surfaces from Single Images in Closed Form
2009. Computer Vision and Pattern Recognition (CVPR). p. 1842 - 1849. DOI : 10.1109/CVPR.2009.5206758.Specularities as an information source in the presence of texture
Lausanne, EPFL, 2009. DOI : 10.5075/epfl-thesis-4387.Training for Task Specific Keypoint Detection
2009. DAGM Symposium on Pattern Recognition, Jena, GERMANY, Sep 09-11, 2009. p. 151 - 160. DOI : 10.1007/978-3-642-03798-6_16.Image Summaries using Database Saliency
2009. The 2nd ACM SIGGRAPH Conference and Exhibition in Asia (SIGGRAPH Asia), Yokohama, Japan, December 16-19, 2009. DOI : 10.1145/1666778.1666821.Appearance-based Keypoint Clustering
2009. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009), Miami Beach, FL, USA, June 20-25, 2009. DOI : 10.1109/CVPR.2009.5206514.Evaluation of Probabilistic Occupancy Map People Detection for Surveillance Systems
2009. IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Miami, Florida, USA, June 20-25, 2009. p. 55 - 62.Compact Signatures for High-speed Interest Point Description and Matching
2009. International Conference on Computer Vision, September, 2009.Steerable Features for Statistical 3D Dendrite Detection
2009. Twelfth International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'09), London, UK, September 20-24, 2009. p. 625 - 632. DOI : 10.1007/978-3-642-04271-3_76.Classification-based Probabilistic Modeling of Texture Transition for Fast Line Search Tracking and Delineation
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2009. DOI : 10.1109/TPAMI.2008.236.Observable Subspaces for 3D Human Motion Recovery
2009. IEEE Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA, June 22 - 24, 2009. p. 1137 - 1144. DOI : 10.1109/CVPR.2009.5206489.View-Based Maps
2009. Robotics: Science and Systems Conference, Seattle, June 2009.Pose Estimation for Category Specific Multiview Object Localization
2009. Conference on Computer Vision and Pattern Recognition, Miami, 2009. p. 778 - 785. DOI : 10.1109/CVPR.2009.5206633.2008
Tracking Articulated Bodies using Generalized Expectation Maximization
2008. CVPR Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment, Anchorage, June 27-28, 2006. DOI : 10.1109/CVPRW.2008.4563073.Automated Delineation of Dendritic Networks in Noisy Image Stacks
2008. European Conference on Computer Vision, Marseille, October 13-16, 2008. p. 214 - 227. DOI : 10.1007/978-3-540-88693-8_16.Linking Pose and Motion
2008. European Conference on Computer Vision, Marseille, October 12-18, 2008. p. 200 - 213. DOI : 10.1007/978-3-540-88693-8_15.3D pose refinement from reflections
2008. IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, Jun 23-28, 2008. p. 1205 - 1212. DOI : 10.1109/CVPR.2008.4587498.Multi-Camera Tracking and Atypical Motion Detection with Behavioral Maps
2008. Proceedings of the 10th European Conference on Computer Vision, Marseille, October 12-18, 2008. p. 112 - 125. DOI : 10.1007/978-3-540-88690-7_9.On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery
2008. IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, June 24-26, 2008. DOI : 10.1109/CVPR.2008.4587706.Pose Priors for Simultaneously Solving Alignment and Correspondence
2008. European Conference on Computer Vision, Marseille, France, Oct 12-18, 2008. p. 405 - 418. DOI : 10.1007/978-3-540-88688-4_30.Local deformation models for monocular 3D shape recovery
2008. IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, Jun 23-28, 2008. p. 1213 - 1220. DOI : 10.1109/CVPR.2008.4587499.Multi-Camera People Tracking with a Probabilistic Occupancy Map
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008. DOI : 10.1109/TPAMI.2007.1174.Fast Non-Rigid Surface Detection, Registration and Realistic Augmentation
International Journal of Computer Vision. 2008. DOI : 10.1007/s11263-006-0017-9.Keypoint Signatures for Fast Learning and Recognition
2008. European Conference on Computer Vision, Marseille, FRANCE, Oct 12-18, 2008. p. 58 - 71. DOI : 10.1007/978-3-540-88682-2_6.IA Generative Model for True Orthorectification
2008. ISPRS Congress, Beijing, 2008. p. 303 - 308.Automated Delineation of Dendritic Networks in Noisy Image Stacks
2008. European Conference on Computer Vision. p. 214 - 227. DOI : 10.1007/978-3-540-88693-8_16.Making Background Subtraction Robust to Sudden Illumination Changes
2008. European Conference on Computer Vision, Marseille, France, Oct 12-18, 2008. p. 567 - 580. DOI : 10.1007/978-3-540-88693-8_42.Retrieving multiple light sources in the presence of specular reflections and texture
Computer Vision And Image Understanding. 2008. DOI : 10.1016/j.cviu.2007.11.002.Keypoint Signatures for Fast Learning and Recognition
2008. European Conference on Computer Vision, Marseilles, October 2008. p. 58 - 71. DOI : 10.1007/978-3-540-88682-2_6.Principled Detection-by-Classification from Multiple Views
2008. International Conference on Computer Vision Theory and Applications, Funchal, Madeira, January 22-25, 2008. p. 375 - 382.A Generative Model for True Orthorectification
2008. ISPRS Congress Beijing 2008, Beijing, 2008.Augmented reality for non-rigid surfaces
Lausanne, EPFL, 2008. DOI : 10.5075/epfl-thesis-4192.A fast local descriptor for dense matching
2008. Conference on Computer Vision and Pattern Recognition, Alaska, USA, June 24-26, 2008. DOI : 10.1109/CVPR.2008.4587673.Closed-Form Solution to Non-rigid 3D Surface Registration
2008. European Conference on Computer Vision, Marseille, FRANCE, Oct 12-18, 2008. p. 581 - 594. DOI : 10.1007/978-3-540-88693-8_43.2007
Accurate non-iterative O(n) solution to the PnP problem
2007. 11th IEEE International Conference on Computer Vision, Rio de Janeiro, BRAZIL, Oct 14-21, 2007. p. 2252 - 2259. DOI : 10.1109/ICCV.2007.4409116.Spatio-temporal human pose detection
Lausanne, EPFL, 2007. DOI : 10.5075/epfl-thesis-3903.Surface Deformation Models for Non-Rigid 3--D Shape Recovery
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2007. DOI : 10.1109/TPAMI.2007.1080.Fast Keypoint Recognition in Ten Lines of Code
2007. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, June 18-23, 2007. DOI : 10.1109/CVPR.2007.383123.Robust Multi-View Change Detection
2007. British Machine Vision Conference, Warwick, September 10-13, 2007. p. 72.1 - 72.10. DOI : 10.5244/C.21.72.Retexturing in the Presence of Complex Illumination and Occlusions
2007. International Symposium on Mixed and Augmented Reality, Nara, Japan, November, 2007.Accurate Non-Iterative O(n) Solution to the PnP Problem
2007. International Conference on Computer Vision, 2007.Implicit Meshes for Effective Silhouette Handling
International Journal of Computer Vision. 2007. DOI : 10.1007/s11263-006-8595-0.Bridging the Gap between Detection and Tracking for 3D Monocular Video-Based Motion Capture
2007. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, June 17-22, 2007. p. 1 - 8. DOI : 10.1109/CVPR.2007.383297.2006
Temporal Motion Models for Monocular and Multiview 3–D Human Body Tracking
Computer Vision and Image Understanding. 2006. DOI : 10.1016/j.cviu.2006.08.006.Estimation and visualization of sagittal kinematics of lower limbs orientation using body-fixed sensors
Ieee Transactions on Biomedical Engineering. 2006. DOI : 10.1109/TBME.2006.873678.An all-in-one solution to geometric and photometric calibration
2006. International Symposium on Mixed and Augmented Reality, Santa Barbara, CA, October 2006. DOI : 10.1109/ISMAR.2006.297796.3D people tracking with Gaussian process dynamical models
2006. Computer Vision and Pattern Recognition, June, 2006. p. 238 - 245. DOI : 10.1109/CVPR.2006.15.Implicit Meshes for Surface Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006. DOI : 10.1109/TPAMI.2006.37.Robust People Tracking with Global Trajectory Optimization
2006. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, June 17-22, 2006. p. 744 - 750. DOI : 10.1109/CVPR.2006.258.Keypoint Recognition using Randomized Trees
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006. DOI : 10.1109/TPAMI.2006.188.Motion models for robust 3D human body tracking
Lausanne, EPFL, 2006. DOI : 10.5075/epfl-thesis-3541.Dendrite Tracking in Microscopic Images using Minimum Spanning Trees and Localized E-M
2006Human body pose detection using Bayesian spatio-temporal templates
Computer Vision and Image Understanding. 2006. DOI : 10.1016/j.cviu.2006.07.007.Feature Harvesting for Tracking-by-Detection
2006. European Conference on Computer Vision, Graz, May 7-13, 2006. p. 592 - 605. DOI : 10.1007/11744078_46.2005
Classifier-based Contour Tracking for Rigid and Deformable Objects
2005. British Machine Vision Conference. p. 56.1 - 56.10. DOI : 10.5244/C.19.56.Real-Time Non-Rigid Surface Detection
2005. Conference on Computer Vision and Pattern Recognition, San Diego, CA. p. 822 - 828. DOI : 10.1109/CVPR.2005.293.Implicit meshes : unifying implicit and explicit surface representations for 3D reconstruction and tracking
Lausanne, EPFL, 2005. DOI : 10.5075/epfl-thesis-3243.Probabilistic modeling of texture transition for fast tracking and delineation
Lausanne, EPFL, 2005. DOI : 10.5075/epfl-thesis-3377.Augmenting Deformable Objects in Real-Time
2005. International Symposium on Mixed and Augmented Reality, Vienna, Austria, October 2005. p. 134 - 137. DOI : 10.1109/ISMAR.2005.18.Multiple Light Sources Recovery in the Presence of Specularities and Texture
2005Human Body Pose Recognition Using Spatio-Temporal Templates
2005. ICCV workshop on Modeling People and Human Interaction, Beijing, China.Physically Valid Shape Parameterization for Monocular 3-D Deformable Surface Tracking
2005. p. 12.1 - 12.10. DOI : 10.5244/C.19.12.Randomized Trees for Real-Time Keypoint Recognition
2005. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA. p. 775 - 781. DOI : 10.1109/CVPR.2005.288.Priors for People Tracking from Small Training Sets
2005. International Conference in Computer Vision. p. 403 - 410. DOI : 10.1109/ICCV.2005.193.Implicit Surfaces Make for Better Silhouettes
2005. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA. p. 1135 - 1142. DOI : 10.1109/CVPR.2005.185.Monocular 3--D Tracking of the Golf Swing
2005. Conference on Computer Vision and Pattern Recognition, San Diego. p. 932 - 939. DOI : 10.1109/CVPR.2005.229.Hierarchical Implicit Surface Joint Limits for Human Body Tracking
Computer Vision and Image Understanding. 2005. DOI : 10.1016/j.cviu.2005.01.005.Fast Texture-Based Tracking and Delineation Using Texture Entropy
2005. p. 1154 - 1160. DOI : 10.1109/ICCV.2005.97.Monocular Model-Based 3D Tracking of Rigid Objects: A Survey
Foundations and Trends in Computer Graphics and Vision. 2005. DOI : 10.1561/0600000001.Real-Time Non-Rigid Surface Detection
2005. Conference on Computer Vision and Pattern Recognition, San Diego, CA, June 2005. p. 822 - 828. DOI : 10.1109/CVPR.2005.293.Fixed Point Probability Field for Complex Occlusion Handling
2005. p. 694 - 700. DOI : 10.1109/ICCV.2005.102.Parameterizing Deformable Surfaces for Monocular 3--D Tracking
2005An Investigation of Model Bias in 3D Face Tracking
2005. Conference on Analysis and Modelling of Faces and Gestures. p. 125 - 139. DOI : 10.1007/11564386_11.2004
Randomized Trees for Real-Time Keypoint Recognition
2004Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture
2004. European Conference on Computer Vision, Prague, Czech Republic. p. 405 - 418. DOI : 10.1007/978-3-540-24671-8_32.Monocular 3-D Tracking of the Golf Swing
2004Using biomechanical constraints to improve video-based motion capture
Lausanne, EPFL, 2004. DOI : 10.5075/epfl-thesis-2892.Mahalanobis Motion Generation
2004Accurate Face Models from Uncalibrated and Ill-Lit Video Sequences
2004A Stable Real-Time AR Framework for Training and Planning in Industrial Environments
2004. p. 129 - 146. DOI : 10.1007/978-1-4471-3873-0_8.Fast Texture-Based Tracking and Delineation Using Texture Entropy
20043--D Motion Analysis and Synthesis from Inertial Gyroscopes and Image Data
2004.Fixed Point Probability Field for Occlusion Handling
2004Markov-based Silhouette Extraction for Three--Dimensional Body Tracking in Presence of Cluttered Background
2004. British Machine Vision Conference. p. 17.1 - 17.10. DOI : 10.5244/C.18.17.Implicit Meshes for Surface Reconstruction
2004Real-time non-rigid surface detection
20043D Tracking for Gait Characterization and Recognition
2004. DOI : 10.1109/AFGR.2004.1301503.Stable Real-Time 3D Tracking Using Online and Offline Information
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2004. DOI : 10.1109/TPAMI.2004.92.3D human body tracking using deterministic temporal motion models
2004. 8th European Conference on Computer Vision, Prague, CZECH REPUBLIC, May 11-14, 2004. p. 92 - 106. DOI : 10.1007/978-3-540-24672-5_8.Combining Edge and Texture Information for Real-Time Accurate 3D Camera Tracking
2004. International Symposium on Mixed and Augmented Reality, Arlington, VA. DOI : 10.1109/ISMAR.2004.24.Hierarchical Implicit Surface Joint Limits for Human Body Tracking
2004Texture Boundary Detection for Real-Time Tracking
2004.Stable Real-Time AR Framework for Training and Planning in Industrial Environments
Virtual and Augmented Reality Applications in Manufacturing; Springer-Verlag, 2004. p. 129 - 145.Point Matching as a Classification Problem for Fast and Robust Object Pose Estimation
2004. Conference on Computer Vision and Pattern Recognition. DOI : 10.1109/CVPR.2004.1315170.Implicit Meshes Make for Better Silhouettes
2004Style-based Motion Synthesis
Computer Graphics Forum. 2004. DOI : 10.1111/j.1467-8659.2004.00809.x.3D Tracking for Gait Characterization and Recognition
2004Point Matching as a Classification Problem for Fast and Robust Object Pose Estimation
2004Multi modal tracking in complex environments for augmented reality applications
Lausanne, EPFL, 2004. DOI : 10.5075/epfl-thesis-3114.Towards Recognizing Feature Points using Classification Trees
2004Accurate Face Models from Uncalibrated and Ill-Lit Video Sequences
2004. Conference on Computer Vision and Pattern Recognition. DOI : 10.1109/CVPR.2004.1315278.3D Human Body Tracking using Deterministic Temporal Motion Models
20042003
Visual Golf Club Tracking for Enhanced Swing Analysis Tools
2003. British Machine Vision Conference, Norwich, UK. p. 47.1 - 47.10. DOI : 10.5244/C.17.47.From Explicit to Implicit Surfaces for Visualization, Animation and Modeling
2003.Self-consistency and MDL: a paradigm for evaluating point correspondence algorithms and detecting change
International Journal of Computer Vision. 2003. DOI : 10.1023/A:1020940807324.Articulated Soft Objects for Multi-View Shape and Motion Capture
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003. DOI : 10.1109/TPAMI.2003.1227995.Stable Real-Time Interaction Between Virtual Humans and Real Scenes
2003. International Conference on 3-D Digital Imaging and Modeling, Banff, Alberta, Canada. p. 449 - 456. DOI : 10.1109/IM.2003.1240281.Real-time augmented face
2003. International Symposium on Mixed and Augmented Reality. p. 346 - 347. DOI : 10.1109/ISMAR.2003.1240753.Fully Automated and Stable Registration for Augmented Reality Applications
2003. International Symposium on Mixed and Augmented Reality, Tokyo, Japan. DOI : 10.1109/ISMAR.2003.1240692.Generic Deformable Implicit Mesh Models for Automated Reconstruction
2003. ICCV workshop on Higher-Level Knowledge in 3D Modelling and Motion Analysis, Nice, France. p. 29 - 38. DOI : 10.1109/HLK.2003.1240856.Implicit Meshes for Modeling and Reconstruction
2003. Conference on Computer Vision and Pattern Recognition, Madison, WI. DOI : 10.1109/CVPR.2003.1211506.Fusing Online and Offline Information for Stable 3D Tracking in Real-Time
2003. Conference on Computer Vision and Pattern Recognition, Madison, WI, USA. DOI : 10.1109/CVPR.2003.1211476.Least Squares Matching Tracking Algorithm for Human Body Modeling
2003. XIX Congress for the International Society for Photogrammetry and Remote Sensing Congress, Amsterdam, Netherlands, 16-23 July 2003.Robust tracking and segmentation of human motion in an image sequence
2003. p. 29 - 32. DOI : 10.1109/ICASSP.2003.1199099.Bundle Adjustment for Markerless Body Tracking in Monocular Video Sequences
2003.Robust Data Association For Online Applications
2003. DOI : 10.1109/CVPR.2003.1211365.Automatic Determination of Shoulder Joint Limits using Experimentally Determined Quaternion Field Boundaries
International Journal of Robotics Research. 2003. DOI : 10.1177/0278364903022006005.2002
Markerless Full Body Shape and Motion Capture from Video Sequences
2002.Using Dirichlet Free Form Deformation to Fit Deformable Models to Noisy 3-D Data
2002. European Conference on Computer Vision (ECCV), Copenhagen, Denmark. p. 704 - 717. DOI : 10.1007/3-540-47967-8_47.Polyhedral object detection and pose estimation for augmented reality applications
2002. Computer Animation, Geneva, Switzerland. p. 65 - 69. DOI : 10.1109/CA.2002.1017508.Recovery of Reflectances and Varying Illuminants from Multiple Views
2002. European Conference on Computer Vision, Copenhagen, Denmark. p. 163 - 179. DOI : 10.1007/3-540-47977-5_11.An Automatic Method For Determining Quaternion Field Boundaries for Ball-and-Socket Joint Limits
2002. Automated Face and Gesture Recognition, Washington, DC. p. 95 - 100. DOI : 10.1109/AFGR.2002.1004138.Model-Based Silhouette Extraction for Accurate People Tracking
2002. European Conference on Computer Vision, Copenhagen, Denmark. p. 325 - 339. DOI : 10.1007/3-540-47967-8_22.The radiometry of multiple images
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002. DOI : 10.1109/34.982882.2001
On Implicit Modeling for Fitting Purposes
2001. p. 109 - 119. DOI : 10.1007/978-0-306-47002-8_10.Human body modeling from video sequences
Lausanne, EPFL, 2001. DOI : 10.5075/epfl-thesis-2493.Tracking and Modeling People in Video Sequences
Computer Vision and Image Understanding. 2001. DOI : 10.1006/cviu.2000.0891.Interaction Techniques with Virtual Humans in Mixed Environments
2001. International Symposium on Mixed Reality, Tokyo, Japan.Interaction Techniques with Virtual Humans in Mixed Environments
2001.Incorporating Differential Constraints in the 3D Reconstruction Process : Application to Stereo
2001. International Conference on Computer Vision, Vancouver, Canada. p. 573 - 580. DOI : 10.1109/ICCV.2001.937569.Using skeleton-based tracking to increase the reliability of optical motion capture
Human Movement Science. 2001. DOI : 10.1016/S0167-9457(01)00050-1.Articulated Soft Objects for Video-based Body Modeling
2001. International Conference on Computer Vision, Vancouver, Canada. p. 394 - 401. DOI : 10.1109/ICCV.2001.937545.Real-Time 3D Object Recognition for Automatic Tracker Initialization
2001. International Symposium on Augmented Reality, Newyork, USA, 29-30 October, 2001. p. 175 - 176. DOI : 10.1109/ISAR.2001.970529.2000
Interaction Between Real and Virtual Humans: Playing Checkers
2000. Eurographics Workshop On Virtual Environments. p. 23 - 32. DOI : 10.1007/978-3-7091-6785-4_4.3--D Stereo Reconstruction of Human Faces driven by Differential Constraints Image and Vision Computing
Image and Vision Computing. 2000. DOI : 10.1016/S0262-8856(99)00058-X.Human Shape and Motion Recovery Using Animation Models
2000.Selected publications
| R. Achanta, A. Shaj, K. Smith, A. Lucchi, P. Fua, and S. S�sstrunk. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, num. 11, p. 2274 - 2282, 2012. |
SLIC Superpixels Compared to State-of-the-art Superpixel Methods |
| F Fleuret, J Berclaz, R Lengagne, and P Fua Pattern Analysis and Machine Intelligence, 30 (2), 267-282, 2008 |
Multicamera People Tracking with a Probabilistic Occupancy Map |
| V. Lepetit and P. Fua Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, Nr. 9, pp. 1465--1479, 2006. |
Keypoint Recognition using Randomized Trees |
| P. Fua and Y. G. Leclerc International Journal of Computer Vision, Vol. 16, pp. 35-56, 1995. |
Object-Centered Surface Reconstruction: Combining Multi-Image Stereo and Shading |
| P. Fua Machine Vision and Applications, Vol. 6, Nr. 1, pp. 35-49, 1993. |
A Parallel Stereo Algorithm that Produces Dense Depth Maps and Preserves Image Features |
Teaching & PhD
Teaching
Computer Science
Communication Systems
PhD Students
Chen Yihong, Davydov Andrey, Deng Zhantao, Dumery Corentin Camille Marius, Durasov Nikita, Fan Aoxiang, Javed Saqib, Li Ren, Sayin Mercadier Deniz, Stella Federico, Talabot Nicolas, Wei Zhen, Zhang Tianzong, Zhao Chen,Past EPFL PhD Students
Ali Karim , Bagautdinov Timur , Baqué Pierre Bruno , Becker Carlos Joaquin , Bednarík Jan , Ben Shitrit Horesh Beny , Berclaz Jérôme , Bermúdez Chacón Róger , Bhattacharjee Deblina , Calonder Michael , Crivellaro Alberto , Fossati Andrea , Glowacki Przemyslaw Rafal , González Serrano Germán , Guillard Benoît Alain René , Guo Shuxuan , Günel Semih , Honzátko David , Katircioglu Isinsu , Kiciroglu Sena , Konyushkova Ksenia , Lis Krzysztof Maciej , Liu Weizhe , Lucchi Aurélien , Maksai Andrii , Mosinska Agata Justyna , Nakka Krishna Kanth , Ngo Tien Dat , Oner Doruk , Pilet Julien , Remelli Edoardo , Rigamonti Roberto , Rozantsev Artem , Salzmann Mathieu , Sironi Amos , Sun Xiaolu , Tekin Bugra , Tola Engin , Trzcinski Tomasz Piotr , Tyszkiewicz Michal Jan , Türetken Engin , Varol Aydin , Vidit Vidit , Wang Xinchao , Wickramasinghe Pamuditha Udaranga , Yu Kaicheng , Özuysal Mustafa ,Courses
Introduction to machine learning
Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and practically implemented.
Computer vision
Computer Vision aims at modeling the world from digital images acquired using video or infrared cameras, and other imaging sensors.
We will focus on images acquired using digital cameras. We will introduce basic processing techniques and discuss their field of applicability.