Philippe Weinzaepfel

papers

1,468

total citations

papers (20)

Hard Negative Mixing for Contrastive Learning

NEURIPS 2020arXiv

727

citations

CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow

ICCV 2023arXiv

161

citations

CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

NEURIPS 2022arXiv

131

citations

DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild

ECCV 2020arXiv

citations

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

ECCV 2020arXiv

citations

PoseFix: Correcting 3D Human Poses with Natural Language

ICCV 2023arXiv

citations

Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors

CVPR 2025arXiv

citations

UNIC: Universal Classification Models via Multi-teacher Distillation

ECCV 2024arXiv

citations

PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation

ECCV 2024arXiv

citations

Cross-view and Cross-pose Completion for 3D Human Understanding

CVPR 2024arXiv

citations

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction

ICCV 2025arXiv

citations

Kinaema: a recurrent sequence model for memory and pose in motion

NEURIPS 2025arXiv

citations

PoseScript: 3D Human Poses from Natural Language

ECCV 2022

citations

PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors

CVPR 2022

citations

SuperLoss: A Generic Loss for Robust Curriculum Learning

NEURIPS 2020

citations

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers

CVPR 2025

citations

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

ICLR 2024arXiv

citations

Philippe Weinzaepfel

papers (20)

Hard Negative Mixing for Contrastive Learning

CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow

CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

PoseGPT: Quantization-Based 3D Human Motion Generation and Forecasting

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

Large-Scale Localization Datasets in Crowded Indoor Spaces

DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

PoseFix: Correcting 3D Human Poses with Natural Language

Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors

UNIC: Universal Classification Models via Multi-teacher Distillation

PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation

Cross-view and Cross-pose Completion for 3D Human Understanding

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction

Kinaema: a recurrent sequence model for memory and pose in motion

PoseScript: 3D Human Poses from Natural Language

PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors

SuperLoss: A Generic Loss for Robust Curriculum Learning

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

papers (20)

Hard Negative Mixing for Contrastive Learning

CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow

CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

PoseGPT: Quantization-Based 3D Human Motion Generation and Forecasting

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

Large-Scale Localization Datasets in Crowded Indoor Spaces

DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

PoseFix: Correcting 3D Human Poses with Natural Language

Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors

UNIC: Universal Classification Models via Multi-teacher Distillation

PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation

Cross-view and Cross-pose Completion for 3D Human Understanding

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction

Kinaema: a recurrent sequence model for memory and pose in motion

PoseScript: 3D Human Poses from Natural Language

PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors

SuperLoss: A Generic Loss for Robust Curriculum Learning

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency