Philippe Weinzaepfel
Research Subjects
Philippe Weinzaepfel has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Grégory Rogez
Naver Labs Europe
6 shared publications - Fabien Baradel
Naver Labs Europe
3 shared publications - Francesc Moreno-Noguer
Institut de Robòtica i Informàtica Industrial CSIC-UPC
2 shared publications - Guénolé Fiche
Naver Labs Europe
2 shared publications - Romain Brégier
Naver Labs Europe
2 shared publications - Thomas Lucas
Naver Labs Europe
2 shared publications
Latest Publications
- 5 October 2026
- Published by Springer Nature
- p. 641-662
BLASt3R : Bundle Adjustment of Any Image Set with Multi-view Matching and Monocular priors
- 5 October 2026
- Published by Springer Nature
- p. 641-662
BLASt3R : Bundle Adjustment of Any Image Set with Multi-view Matching and Monocular priors
- 4 October 2026
- Published by Springer Nature
- p. 147-165
Sparse Auto-regressive Modeling for Scene Generation from Multi-view Images
- 4 October 2026
- Published by Springer Nature
- p. 147-165
Sparse Auto-regressive Modeling for Scene Generation from Multi-view Images
- 11 September 2026
- Published by Springer Nature
- p. 281-299
Multi-HMR 2: Multi-person Camera-Centric Human Detection, Mesh Recovery and Tracking
- 11 September 2026
- Published by Springer Nature
- p. 281-299
Multi-HMR 2: Multi-person Camera-Centric Human Detection, Mesh Recovery and Tracking
- 30 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (7) , 5146-5159
PoseScript: Linking 3D Human Poses and Natural Language
Natural language plays a critical role in many computer vision applications, such as image captioning, visual question answering, and cross-modal retrieval, to provide fine-grained semantic information. Unfortunately, while human pose is key to human understanding, current 3D human pose datasets lack detailed language descriptions. To address this issue, we have introduced the PoseScript dataset. This dataset pairs more than six thousand 3D human poses from AMASS with rich human-annotated descriptions of the body parts and their spatial relationships. Additionally, to increase the size of the dataset to a scale that is compatible with data-hungry learning algorithms, we have proposed an elaborate captioning process that generates automatic synthetic descriptions in natural language from given 3D keypoints. This process extracts low-level pose information, known as “posecodes”, using a set of simple but generic rules on the 3D keypoints. These posecodes are then combined into higher level textual descriptions using syntactic rules. With automatic annotations, the amount of available data significantly scales up (100k), making it possible to effectively pretrain deep models for finetuning on human captions. To showcase the potential of annotated poses, we present three multi-modal learning tasks that utilize the PoseScript dataset. Firstly, we develop a pipeline that maps 3D poses and textual descriptions into a joint embedding space, allowing for cross-modal retrieval of relevant poses from large-scale datasets. Secondly, we establish a baseline for a text-conditioned model generating 3D poses. Thirdly, we present a learned process for generating pose descriptions. These applications demonstrate the versatility and usefulness of annotated poses in various tasks and pave the way for future research in the field.
- 30 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (7) , 5146-5159
PoseScript: Linking 3D Human Poses and Natural Language
Natural language plays a critical role in many computer vision applications, such as image captioning, visual question answering, and cross-modal retrieval, to provide fine-grained semantic information. Unfortunately, while human pose is key to human understanding, current 3D human pose datasets lack detailed language descriptions. To address this issue, we have introduced the PoseScript dataset. This dataset pairs more than six thousand 3D human poses from AMASS with rich human-annotated descriptions of the body parts and their spatial relationships. Additionally, to increase the size of the dataset to a scale that is compatible with data-hungry learning algorithms, we have proposed an elaborate captioning process that generates automatic synthetic descriptions in natural language from given 3D keypoints. This process extracts low-level pose information, known as “posecodes”, using a set of simple but generic rules on the 3D keypoints. These posecodes are then combined into higher level textual descriptions using syntactic rules. With automatic annotations, the amount of available data significantly scales up (100k), making it possible to effectively pretrain deep models for finetuning on human captions. To showcase the potential of annotated poses, we present three multi-modal learning tasks that utilize the PoseScript dataset. Firstly, we develop a pipeline that maps 3D poses and textual descriptions into a joint embedding space, allowing for cross-modal retrieval of relevant poses from large-scale datasets. Secondly, we establish a baseline for a text-conditioned model generating 3D poses. Thirdly, we present a learned process for generating pose descriptions. These applications demonstrate the versatility and usefulness of annotated poses in various tasks and pave the way for future research in the field.
- Open Access
PoseScript: Linking 3D Human Poses and Natural Language
Natural language plays a critical role in many computer vision applications, such as image captioning, visual question answering, and cross-modal retrieval, to provide fine-grained semantic information. Unfortunately, while human pose is key to human understanding, current 3D human pose datasets lack detailed language descriptions. To address this issue, we have introduced the PoseScript dataset. This dataset pairs more than six thousand 3D human poses from AMASS with rich human-annotated descriptions of the body parts and their spatial relationships. Additionally, to increase the size of the dataset to a scale that is compatible with data-hungry learning algorithms, we have proposed an elaborate captioning process that generates automatic synthetic descriptions in natural language from given 3D keypoints. This process extracts low-level pose information, known as "posecodes", using a set of simple but generic rules on the 3D keypoints. These posecodes are then combined into higher level textual descriptions using syntactic rules. With automatic annotations, the amount of available data significantly scales up (100k), making it possible to effectively pretrain deep models for finetuning on human captions. To showcase the potential of annotated poses, we present three multi-modal learning tasks that utilize the PoseScript dataset. Firstly, we develop a pipeline that maps 3D poses and textual descriptions into a joint embedding space, allowing for cross-modal retrieval of relevant poses from large-scale datasets. Secondly, we establish a baseline for a text-conditioned model generating 3D poses. Thirdly, we present a learned process for generating pose descriptions. These applications demonstrate the versatility and usefulness of annotated poses in various tasks and pave the way for future research in the field.
Open AccessPoseScript: Linking 3D Human Poses and Natural Language
Natural language plays a critical role in many computer vision applications, such as image captioning, visual question answering, and cross-modal retrieval, to provide fine-grained semantic information. Unfortunately, while human pose is key to human understanding, current 3D human pose datasets lack detailed language descriptions. To address this issue, we have introduced the PoseScript dataset. This dataset pairs more than six thousand 3D human poses from AMASS with rich human-annotated descriptions of the body parts and their spatial relationships. Additionally, to increase the size of the dataset to a scale that is compatible with data-hungry learning algorithms, we have proposed an elaborate captioning process that generates automatic synthetic descriptions in natural language from given 3D keypoints. This process extracts low-level pose information, known as "posecodes", using a set of simple but generic rules on the 3D keypoints. These posecodes are then combined into higher level textual descriptions using syntactic rules. With automatic annotations, the amount of available data significantly scales up (100k), making it possible to effectively pretrain deep models for finetuning on human captions. To showcase the potential of annotated poses, we present three multi-modal learning tasks that utilize the PoseScript dataset. Firstly, we develop a pipeline that maps 3D poses and textual descriptions into a joint embedding space, allowing for cross-modal retrieval of relevant poses from large-scale datasets. Secondly, we establish a baseline for a text-conditioned model generating 3D poses. Thirdly, we present a learned process for generating pose descriptions. These applications demonstrate the versatility and usefulness of annotated poses in various tasks and pave the way for future research in the field.
- 12 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-17
PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling
Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain. Although transformers have been recently utilized for body pose sequence modeling, related methods rely on pseudo-ground truth to augment the currently limited training data available for learning such models. In this paper, we introduce PoseBERT, a transformer module that is fully trained on 3D Motion Capture (MoCap) data via masked modeling. It is simple, generic and versatile, as it can be plugged on top of any image-based model to transform it in a video-based model leveraging temporal information. We showcase variants of PoseBERT with different inputs varying from 3D skeleton keypoints to rotations of a 3D parametric model for either the full body (SMPL) or just the hands (MANO). Since PoseBERT training is task agnostic, the model can be applied to several tasks such as pose refinement, future pose prediction or motion completion without finetuning . Our experimental results validate that adding PoseBERT on top of various state-of-the-art pose estimation methods consistently improves their performances, while its low computational cost allows us to use it in a real-time demo for smoothly animating a robotic hand via a webcam. Test code and models are available at https://github.com/naver/posebert .
- 12 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-17
PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling
Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain. Although transformers have been recently utilized for body pose sequence modeling, related methods rely on pseudo-ground truth to augment the currently limited training data available for learning such models. In this paper, we introduce PoseBERT, a transformer module that is fully trained on 3D Motion Capture (MoCap) data via masked modeling. It is simple, generic and versatile, as it can be plugged on top of any image-based model to transform it in a video-based model leveraging temporal information. We showcase variants of PoseBERT with different inputs varying from 3D skeleton keypoints to rotations of a 3D parametric model for either the full body (SMPL) or just the hands (MANO). Since PoseBERT training is task agnostic, the model can be applied to several tasks such as pose refinement, future pose prediction or motion completion without finetuning . Our experimental results validate that adding PoseBERT on top of various state-of-the-art pose estimation methods consistently improves their performances, while its low computational cost allows us to use it in a real-time demo for smoothly animating a robotic hand via a webcam. Test code and models are available at https://github.com/naver/posebert .
- 25 May 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 130 (7) , 1811-1836
Investigating the Role of Image Retrieval for Visual Localization
- 25 May 2022
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 130 (7) , 1811-1836
Investigating the Role of Image Retrieval for Visual Localization
- 2 March 2021
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 129 (5) , 1675-1690
Mimetics: Towards Understanding Human Actions Out of Context
- 2 March 2021
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 129 (5) , 1675-1690
Mimetics: Towards Understanding Human Actions Out of Context
- 13 November 2020
- Published by Springer Nature
- p. 380-397
DOPE: Distillation of Part Experts for Whole-Body 3D Pose Estimation in the Wild
- 13 November 2020
- Published by Springer Nature
- p. 380-397
DOPE: Distillation of Part Experts for Whole-Body 3D Pose Estimation in the Wild