Papers › Leveraging MoCap Data for Human Mesh Recovery
Leveraging MoCap Data for Human Mesh Recovery
Fabien Baradel, Thibault Groueix, Philippe Weinzaepfel, Romain Brégier, Yannis Kalantidis, Grégory Rogez
Training state-of-the-art models for human body pose and shape recovery from images or videos requires datasets with corresponding annotations that are really hard and expensive to obtain. Our goal in this paper is to study whether poses from 3D Motion Capture (MoCap) data can be used to improve image-based and video-based human mesh recovery methods. We find that fine-tune image-based models with synthetic renderings from MoCap data can increase their performance, by providing them with a wider variety of poses, textures and backgrounds. In fact, we show that simply fine-tuning the batch normalization layers of the model is enough to achieve large gains. We further study the use of MoCap data for video, and introduce PoseBERT, a transformer module that directly regresses the pose parameters and is trained via masked modeling. It is simple, generic and can be plugged on top of any state-of-the-art image-based model in order to transform it in a video-based model leveraging temporal information. Our experimental results show that the proposed approaches reach state-of-the-art performance on various datasets including 3DPW, MPI-INF-3DHP, MuPoTS-3D, MCB and AIST. Test code and models will be available soon.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | 3DPW | MoCap-SPIN + PoseBERT | Acceleration Error | 8.3 | #55 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | MoCap-SPIN + PoseBERT | MPJPE | 89.4 | #55 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | MoCap-SPIN + PoseBERT | MPVPE | 103.8 | #55 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | MoCap-SPIN + PoseBERT | PA-MPJPE | 52.9 | #55 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | MoCap-SPIN + PoseBERT | Acceleration Error | 8.7 | #64 of 108 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | MoCap-SPIN + PoseBERT | MPJPE | 97.4 | #64 of 108 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | MoCap-SPIN + PoseBERT | PA-MPJPE | 63.3 | #64 of 108 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections