Philippe Weinzaepfel

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers CVPR 2025 HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction ICCV 2025 Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors CVPR 2025 Cross-view and Cross-pose Completion for 3D Human Understanding CVPR 2024 End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon ICLR 2024 Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot ECCV 2024 "PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation" ECCV 2024 UNIC: Universal Classification Models via Multi-teacher Distillation ECCV 2024 Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency ICLR 2024 Win-Win: Training High-Resolution Vision Transformers from Two Windows ICLR 2024 CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow ICCV 2023 PoseFix: Correcting 3D Human Poses with Natural Language ICCV 2023 Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images AAAI 2022 CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion NeurIPS 2022 Learning Super-Features for Image Retrieval ICLR 2022 PoseGPT: Quantization-Based 3D Human Motion Generation and Forecasting ECCV 2022 PoseScript: 3D Human Poses from Natural Language ECCV 2022 PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors CVPR 2022 Large-Scale Localization Datasets in Crowded Indoor Spaces CVPR 2021 DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild ECCV 2020 Hard Negative Mixing for Contrastive Learning NeurIPS 2020 Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction ECCV 2020 SuperLoss: A Generic Loss for Robust Curriculum Learning NeurIPS 2020 MARS: Motion-Augmented RGB Stream for Action Recognition CVPR 2019 R2D2: Reliable and Repeatable Detector and Descriptor NeurIPS 2019 Visual Localization by Learning Objects-Of-Interest Dense Match Regression CVPR 2019 PoTion: Pose MoTion Representation for Action Recognition CVPR 2018 Action Tubelet Detector for Spatio-Temporal Action Localization ICCV 2017 Joint Learning of Object and Action Detectors ICCV 2017 LCR-Net: Localization-Classification-Regression for Human Pose CVPR 2017 EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow CVPR 2015 Learning to Detect Motion Boundaries CVPR 2015 Learning to Track for Spatio-Temporal Action Localization ICCV 2015 DeepFlow: Large Displacement Optical Flow with Deep Matching ICCV 2013