Philippe Weinzaepfel

96 papers A* 28A 1Journal 51Unranked 15
YearRankTypeTitle / Venue / Authors
2025 — conf
CondiMen: Conditional Multi-Person Mesh Recovery.
CVPR Workshops
Romain Brégier, Fabien Baradel, Thomas Lucas, Salma Galaaoui, Matthieu Armando, Philippe Weinzaepfel, Grégory Rogez
2025 A* conf
DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers.
CVPR
Mert Bülent Sariyildiz, Philippe Weinzaepfel, Thomas Lucas, Pau de Jorge, Diane Larlus, Yannis Kalantidis
2025 J jnl
DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers.
CoRR
Mert Bülent Sariyildiz, Philippe Weinzaepfel, Thomas Lucas, Pau de Jorge, Diane Larlus, Yannis Kalantidis
2025 J jnl
HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction.
CoRR
Sara Rojas, Matthieu Armando, Bernard Ghamen, Philippe Weinzaepfel, Vincent Leroy, Grégory Rogez
2025 — conf
HOSt3R: Keypoint-Free Hand-Object 3D Reconstruction from RGB Images.
ICCVW
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel, Jean-Sébastien Franco, Grégory Rogez
2025 J jnl
HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images.
CoRR
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel, Jean-Sébastien Franco, Grégory Rogez
2025 J jnl
Human Mesh Modeling for Anny Body.
CoRR
Romain Brégier, Guénolé Fiche, Laura Bravo-Sánchez, Thomas Lucas, Matthieu Armando, Philippe Weinzaepfel, Grégory Rogez, Fabien Baradel
2025 J jnl
Kinaema: a recurrent sequence model for memory and pose in motion.
CoRR
Mert Bülent Sariyildiz, Philippe Weinzaepfel, Guillaume Bono, Gianluca Monaci, Christian Wolf
2025 — conf
MASt3R-SfM: A Fully-Integrated Solution for Unconstrained Structure-from-Motion.
3DV
Bardienus Pieter Duisterhof, Lojze Zust, Philippe Weinzaepfel, Vincent Leroy, Yohann Cabon, Jérôme Revaud
2025 J jnl
PoseScript: Linking 3D Human Poses and Natural Language.
IEEE Trans. Pattern Anal. Mach. Intell.
Ginger Delmas, Philippe Weinzaepfel, Thomas Lucas, Francesc Moreno-Noguer, Grégory Rogez
2025 A* conf
Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors.
CVPR
Wonbong Jang, Philippe Weinzaepfel, Vincent Leroy, Lourdes Agapito, Jérôme Revaud
2025 J jnl
Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors.
CoRR
Wonbong Jang, Philippe Weinzaepfel, Vincent Leroy, Lourdes Agapito, Jérôme Revaud
2025 J jnl
What does really matter in image goal navigation?
CoRR
Gianluca Monaci, Philippe Weinzaepfel, Christian Wolf
2024 J jnl
CondiMen: Conditional Multi-Person Mesh Recovery.
CoRR
Romain Brégier, Fabien Baradel, Thomas Lucas, Salma Galaaoui, Matthieu Armando, Philippe Weinzaepfel, Grégory Rogez
2024 A* conf
Cross-View and Cross-Pose Completion for 3D Human Understanding.
CVPR
Matthieu Armando, Salma Galaaoui, Fabien Baradel, Thomas Lucas, Vincent Leroy, Romain Brégier, Philippe Weinzaepfel, Grégory Rogez
2024 A* conf
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon.
ICLR
Guillaume Bono, Leonid Antsfeld, Boris Chidlovskii, Philippe Weinzaepfel, Christian Wolf
2024 J jnl
MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion.
CoRR
Bardienus Pieter Duisterhof, Lojze Zust, Philippe Weinzaepfel, Vincent Leroy, Yohann Cabon, Jérôme Revaud
2024 J jnl
Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot.
CoRR
Fabien Baradel, Matthieu Armando, Salma Galaaoui, Romain Brégier, Philippe Weinzaepfel, Grégory Rogez, Thomas Lucas
2024 — conf
Multi-HMR: Multi-person Whole-Body Human Mesh Recovery in a Single Shot.
ECCV (23)
Fabien Baradel, Matthieu Armando, Salma Galaaoui, Romain Brégier, Philippe Weinzaepfel, Grégory Rogez, Thomas Lucas
2024 — conf
PoseEmbroider: Towards a 3D, Visual, Semantic-Aware Human Pose Representation.
ECCV (71)
Ginger Delmas, Philippe Weinzaepfel, Francesc Moreno-Noguer, Grégory Rogez
2024 J jnl
PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation.
CoRR
Ginger Delmas, Philippe Weinzaepfel, Francesc Moreno-Noguer, Grégory Rogez
2024 — conf
Purposer: Putting Human Motion Generation in Context.
3DV
Nicolas Ugrinovic, Thomas Lucas, Fabien Baradel, Philippe Weinzaepfel, Grégory Rogez, Francesc Moreno-Noguer
2024 J jnl
Purposer: Putting Human Motion Generation in Context.
CoRR
Nicolas Ugrinovic, Thomas Lucas, Fabien Baradel, Philippe Weinzaepfel, Grégory Rogez, Francesc Moreno-Noguer
2024 — conf
SACReg: Scene-Agnostic Coordinate Regression for Visual Localization.
CVPR Workshops
Jérôme Revaud, Yohann Cabon, Romain Brégier, Jongmin Lee, Philippe Weinzaepfel
2024 J jnl
SHOWMe: Robust object-agnostic hand-object 3D reconstruction from RGB video.
Comput. Vis. Image Underst.
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel, Fabien Baradel, Salma Galaaoui, Romain Brégier, Matthieu Armando, Jean-Sébastien Franco, Grégory Rogez
2024 — conf
UNIC: Universal Classification Models via Multi-teacher Distillation.
ECCV (4)
Mert Bülent Sariyildiz, Philippe Weinzaepfel, Thomas Lucas, Diane Larlus, Yannis Kalantidis
2024 J jnl
UNIC: Universal Classification Models via Multi-teacher Distillation.
CoRR
Mert Bülent Sariyildiz, Philippe Weinzaepfel, Thomas Lucas, Diane Larlus, Yannis Kalantidis
2024 A* conf
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency.
ICLR
Yannis Kalantidis, Mert Bülent Sariyildiz, Rafael S. Rezende, Philippe Weinzaepfel, Diane Larlus, Gabriela Csurka
2024 J jnl
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency.
CoRR
Yannis Kalantidis, Mert Bülent Sariyildiz, Rafael Sampaio de Rezende, Philippe Weinzaepfel, Diane Larlus, Gabriela Csurka
2024 A* conf
Win-Win: Training High-Resolution Vision Transformers from Two Windows.
ICLR
Vincent Leroy, Jérôme Revaud, Thomas Lucas, Philippe Weinzaepfel
2023 A* conf
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow.
ICCV
Philippe Weinzaepfel, Thomas Lucas, Vincent Leroy, Yohann Cabon, Vaibhav Arora, Romain Brégier, Gabriela Csurka, Leonid Antsfeld, Boris Chidlovskii, Jérôme Revaud
2023 J jnl
Cross-view and Cross-pose Completion for 3D Human Understanding.
CoRR
Matthieu Armando, Salma Galaaoui, Fabien Baradel, Thomas Lucas, Vincent Leroy, Romain Brégier, Philippe Weinzaepfel, Grégory Rogez
2023 J jnl
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon.
CoRR
Guillaume Bono, Leonid Antsfeld, Boris Chidlovskii, Philippe Weinzaepfel, Christian Wolf
2023 J jnl
PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling.
IEEE Trans. Pattern Anal. Mach. Intell.
Fabien Baradel, Romain Brégier, Thibault Groueix, Philippe Weinzaepfel, Yannis Kalantidis, Grégory Rogez
2023 A* conf
PoseFix: Correcting 3D Human Poses with Natural Language.
ICCV
Ginger Delmas, Philippe Weinzaepfel, Francesc Moreno-Noguer, Grégory Rogez
2023 J jnl
PoseFix: Correcting 3D Human Poses with Natural Language.
CoRR
Ginger Delmas, Philippe Weinzaepfel, Francesc Moreno-Noguer, Grégory Rogez
2023 J jnl
SACReg: Scene-Agnostic Coordinate Regression for Visual Localization.
CoRR
Jérôme Revaud, Yohann Cabon, Romain Brégier, Jongmin Lee, Philippe Weinzaepfel
2023 — conf
SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction.
ICCV (Workshops)
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel, Fabien Baradel, Salma Galaaoui, Romain Brégier, Matthieu Armando, Jean-Sébastien Franco, Grégory Rogez
2023 J jnl
SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction.
CoRR
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel, Fabien Baradel, Salma Galaaoui, Romain Brégier, Matthieu Armando, Jean-Sébastien Franco, Grégory Rogez
2023 J jnl
Win-Win: Training High-Resolution Vision Transformers from Two Windows.
CoRR
Vincent Leroy, Jérôme Revaud, Thomas Lucas, Philippe Weinzaepfel
2022 A* conf
Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images.
AAAI
Thomas Lucas, Philippe Weinzaepfel, Grégory Rogez
2022 A* conf
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion.
NeurIPS
Philippe Weinzaepfel, Vincent Leroy, Thomas Lucas, Romain Brégier, Yohann Cabon, Vaibhav Arora, Leonid Antsfeld, Boris Chidlovskii, Gabriela Csurka, Jérôme Revaud
2022 J jnl
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion.
CoRR
Philippe Weinzaepfel, Vincent Leroy, Thomas Lucas, Romain Brégier, Yohann Cabon, Vaibhav Arora, Leonid Antsfeld, Boris Chidlovskii, Gabriela Csurka, Jérôme Revaud
2022 J jnl
Improved Cross-view Completion Pre-training for Stereo Matching.
CoRR
Philippe Weinzaepfel, Vaibhav Arora, Yohann Cabon, Thomas Lucas, Romain Brégier, Vincent Leroy, Gabriela Csurka, Leonid Antsfeld, Boris Chidlovskii, Jérôme Revaud
2022 J jnl
Investigating the Role of Image Retrieval for Visual Localization - An exhaustive benchmark.
CoRR
Martin Humenberger, Yohann Cabon, Noé Pion, Philippe Weinzaepfel, Donghwan Lee, Nicolas Guérin, Torsten Sattler, Gabriela Csurka
2022 J jnl
Investigating the Role of Image Retrieval for Visual Localization.
Int. J. Comput. Vis.
Martin Humenberger, Yohann Cabon, Noé Pion, Philippe Weinzaepfel, Donghwan Lee, Nicolas Guérin, Torsten Sattler, Gabriela Csurka
2022 A* conf
Learning Super-Features for Image Retrieval.
ICLR
Philippe Weinzaepfel, Thomas Lucas, Diane Larlus, Yannis Kalantidis
2022 J jnl
Learning Super-Features for Image Retrieval.
CoRR
Philippe Weinzaepfel, Thomas Lucas, Diane Larlus, Yannis Kalantidis
2022 A conf
Multi-Finger Grasping Like Humans.
IROS
Yuming Du, Philippe Weinzaepfel, Vincent Lepetit, Romain Brégier
2022 J jnl
Multi-Finger Grasping Like Humans.
CoRR
Yuming Du, Philippe Weinzaepfel, Vincent Lepetit, Romain Brégier
2022 A* conf
PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors.
CVPR
Jérôme Revaud, Vincent Leroy, Philippe Weinzaepfel, Boris Chidlovskii
2022 J jnl
PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling.
CoRR
Fabien Baradel, Romain Brégier, Thibault Groueix, Philippe Weinzaepfel, Yannis Kalantidis, Grégory Rogez
2022 — conf
PoseGPT: Quantization-Based 3D Human Motion Generation and Forecasting.
ECCV (6)
Thomas Lucas, Fabien Baradel, Philippe Weinzaepfel, Grégory Rogez
2022 J jnl
PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting.
CoRR
Thomas Lucas, Fabien Baradel, Philippe Weinzaepfel, Grégory Rogez
2022 — conf
PoseScript: 3D Human Poses from Natural Language.
ECCV (6)
Ginger Delmas, Philippe Weinzaepfel, Thomas Lucas, Francesc Moreno-Noguer, Grégory Rogez
2022 J jnl
PoseScript: 3D Human Poses from Natural Language.
CoRR
Ginger Delmas, Philippe Weinzaepfel, Thomas Lucas, Francesc Moreno-Noguer, Grégory Rogez
2021 J jnl
Barely-Supervised Learning: Semi-Supervised Learning with very few labeled images.
CoRR
Thomas Lucas, Philippe Weinzaepfel, Grégory Rogez
2021 A* conf
Large-Scale Localization Datasets in Crowded Indoor Spaces.
CVPR
Donghwan Lee, Soo-Hyun Ryu, Suyong Yeon, Yonghan Lee, Deokhwa Kim, Cheolho Han, Yohann Cabon, Philippe Weinzaepfel, Nicolas Guérin, Gabriela Csurka, Martin Humenberger
2021 J jnl
Large-scale Localization Datasets in Crowded Indoor Spaces.
CoRR
Donghwan Lee, Soo-Hyun Ryu, Suyong Yeon, Yonghan Lee, Deokhwa Kim, Cheolho Han, Yohann Cabon, Philippe Weinzaepfel, Nicolas Guérin, Gabriela Csurka, Martin Humenberger
2021 — conf
Leveraging MoCap Data for Human Mesh Recovery.
3DV
Fabien Baradel, Thibault Groueix, Philippe Weinzaepfel, Romain Brégier, Yannis Kalantidis, Grégory Rogez
2021 J jnl
Leveraging MoCap Data for Human Mesh Recovery.
CoRR
Fabien Baradel, Thibault Groueix, Philippe Weinzaepfel, Romain Brégier, Yannis Kalantidis, Grégory Rogez
2021 J jnl
Mimetics: Towards Understanding Human Actions Out of Context.
Int. J. Comput. Vis.
Philippe Weinzaepfel, Grégory Rogez
2021 A* conf
Multi-FinGAN: Generative Coarse-To-Fine Sampling of Multi-Finger Grasps.
ICRA
Jens Lundell, Enric Corona, Tran Nguyen Le, Francesco Verdoja, Philippe Weinzaepfel, Grégory Rogez, Francesc Moreno-Noguer, Ville Kyrki
2020 J jnl
DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild.
CoRR
Philippe Weinzaepfel, Romain Brégier, Hadrien Combaluzier, Vincent Leroy, Grégory Rogez
2020 — conf
DOPE: Distillation of Part Experts for Whole-Body 3D Pose Estimation in the Wild.
ECCV (26)
Philippe Weinzaepfel, Romain Brégier, Hadrien Combaluzier, Vincent Leroy, Grégory Rogez
2020 A* conf
Hard Negative Mixing for Contrastive Learning.
NeurIPS
Yannis Kalantidis, Mert Bülent Sariyildiz, Noé Pion, Philippe Weinzaepfel, Diane Larlus
2020 J jnl
Hard Negative Mixing for Contrastive Learning.
CoRR
Yannis Kalantidis, Mert Bülent Sariyildiz, Noé Pion, Philippe Weinzaepfel, Diane Larlus
2020 J jnl
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images.
IEEE Trans. Pattern Anal. Mach. Intell.
Grégory Rogez, Philippe Weinzaepfel, Cordelia Schmid
2020 — conf
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation Under Hand-Object Interaction.
ECCV (23)
Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek, Shreyas Hampali, Mahdi Rad, Zhaohui Zhang, Shipeng Xie, Mingxiu Chen, Boshen Zhang, Fu Xiong, Yang Xiao, Zhiguo Cao, Junsong Yuan, Pengfei Ren, Weiting Huang, Haifeng Sun, Marek Hrúz, Jakub Kanis, Zdenek Krnoul, Qingfu Wan, Shile Li, Linlin Yang, Dongheui Lee, Angela Yao, Weiguo Zhou, Sijia Mei, Yunhui Liu, Adrian Spurr, Umar Iqbal, Pavlo Molchanov, Philippe Weinzaepfel, Romain Brégier, Grégory Rogez, Vincent Lepetit, Tae-Kyun Kim
2020 J jnl
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction.
CoRR
Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek, Shreyas Hampali, Mahdi Rad, Zhaohui Zhang, Shipeng Xie, Mingxiu Chen, Boshen Zhang, Fu Xiong, Yang Xiao, Zhiguo Cao, Junsong Yuan, Pengfei Ren, Weiting Huang, Haifeng Sun, Marek Hrúz, Jakub Kanis, Zdenek Krnoul, Qingfu Wan, Shile Li, Linlin Yang, Dongheui Lee, Angela Yao, Weiguo Zhou, Sijia Mei, Yunhui Liu, Adrian Spurr, Umar Iqbal, Pavlo Molchanov, Philippe Weinzaepfel, Romain Brégier, Grégory Rogez, Vincent Lepetit, Tae-Kyun Kim
2020 J jnl
Multi-FinGAN: Generative Coarse-To-Fine Sampling of Multi-Finger Grasps.
CoRR
Jens Lundell, Enric Corona, Tran Nguyen Le, Francesco Verdoja, Philippe Weinzaepfel, Grégory Rogez, Francesc Moreno-Noguer, Ville Kyrki
2020 — conf
SMPLy Benchmarking 3D Human Pose Estimation in the Wild.
3DV
Vincent Leroy, Philippe Weinzaepfel, Romain Brégier, Hadrien Combaluzier, Grégory Rogez
2020 J jnl
SMPLy Benchmarking 3D Human Pose Estimation in the Wild.
CoRR
Vincent Leroy, Philippe Weinzaepfel, Romain Brégier, Hadrien Combaluzier, Grégory Rogez
2020 A* conf
SuperLoss: A Generic Loss for Robust Curriculum Learning.
NeurIPS
Thibault Castells, Philippe Weinzaepfel, Jérôme Revaud
2019 A* conf
MARS: Motion-Augmented RGB Stream for Action Recognition.
CVPR
Nieves Crasto, Philippe Weinzaepfel, Karteek Alahari, Cordelia Schmid
2019 J jnl
Mimetics: Towards Understanding Human Actions Out of Context.
CoRR
Philippe Weinzaepfel, Grégory Rogez
2019 A* conf
R2D2: Reliable and Repeatable Detector and Descriptor.
NeurIPS
Jérôme Revaud, César Roberto de Souza, Martin Humenberger, Philippe Weinzaepfel
2019 J jnl
R2D2: Repeatable and Reliable Detector and Descriptor.
CoRR
Jérôme Revaud, Philippe Weinzaepfel, César Roberto de Souza, Noé Pion, Gabriela Csurka, Yohann Cabon, Martin Humenberger
2019 A* conf
Visual Localization by Learning Objects-Of-Interest Dense Match Regression.
CVPR
Philippe Weinzaepfel, Gabriela Csurka, Yohann Cabon, Martin Humenberger
2018 J jnl
LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images.
CoRR
Grégory Rogez, Philippe Weinzaepfel, Cordelia Schmid
2018 A* conf
PoTion: Pose MoTion Representation for Action Recognition.
CVPR
Vasileios Choutas, Philippe Weinzaepfel, Jérôme Revaud, Cordelia Schmid
2017 A* conf
Action Tubelet Detector for Spatio-Temporal Action Localization.
ICCV
Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, Cordelia Schmid
2017 J jnl
Action Tubelet Detector for Spatio-Temporal Action Localization.
CoRR
Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, Cordelia Schmid
2017 A* conf
Joint Learning of Object and Action Detectors.
ICCV
Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, Cordelia Schmid
2017 A* conf
LCR-Net: Localization-Classification-Regression for Human Pose.
CVPR
Grégory Rogez, Philippe Weinzaepfel, Cordelia Schmid
2016 J jnl
DeepMatching: Hierarchical Deformable Dense Matching.
Int. J. Comput. Vis.
Jérôme Revaud, Philippe Weinzaepfel, Zaïd Harchaoui, Cordelia Schmid
2016 — —
Motion in action : optical flow estimation and action localization in videos. (Le mouvement en action : estimation du flot optique et localisation d'actions dans les vidéos).
Philippe Weinzaepfel
2016 J jnl
Towards Weakly-Supervised Action Localization.
CoRR
Philippe Weinzaepfel, Xavier Martin, Cordelia Schmid
2015 J jnl
Deep Convolutional Matching.
CoRR
Jérôme Revaud, Philippe Weinzaepfel, Zaïd Harchaoui, Cordelia Schmid
2015 J jnl
EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow.
CoRR
Jérôme Revaud, Philippe Weinzaepfel, Zaïd Harchaoui, Cordelia Schmid
2015 A* conf
EpicFlow: Edge-preserving interpolation of correspondences for optical flow.
CVPR
Jérôme Revaud, Philippe Weinzaepfel, Zaïd Harchaoui, Cordelia Schmid
2015 A* conf
Learning to Track for Spatio-Temporal Action Localization.
ICCV
Philippe Weinzaepfel, Zaïd Harchaoui, Cordelia Schmid
2015 A* conf
Learning to detect Motion Boundaries.
CVPR
Philippe Weinzaepfel, Jérôme Revaud, Zaïd Harchaoui, Cordelia Schmid
2015 J jnl
Learning to track for spatio-temporal action localization.
CoRR
Philippe Weinzaepfel, Zaïd Harchaoui, Cordelia Schmid
2013 A* conf
DeepFlow: Large Displacement Optical Flow with Deep Matching.
ICCV
Philippe Weinzaepfel, Jérôme Revaud, Zaïd Harchaoui, Cordelia Schmid
2011 A* conf
Reconstructing an image from its local descriptors.
CVPR
Philippe Weinzaepfel, Hervé Jégou, Patrick Pérez