Papers › TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking
TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking
N. Dinesh Reddy, Laurent Guigues, Leonid Pischulini, Jayan Eledath, Srinivasa Narasimhan
We consider the task of 3D pose estimation and tracking of multiple people seen in an arbitrary number of camera feeds. We propose TesseTrack, a novel top-down approach that simultaneously reasons about multiple individuals’ 3D body joint reconstructions and associations in space and time in a single end-to-end learnable framework. At the core of our approach is a novel spatio-temporal formulation that operates in a common voxelized feature space aggregated from single- or multiple camera views. After a person detection step, a 4D CNN produces short-term person-specific representations which are then linked across time by a differentiable matcher. The linked descriptions are then merged and deconvolved into 3D poses. This joint spatio-temporal formulation contrasts with previous piece-wise strategies that treat 2D pose estimation, 2D-to-3D lifting, and 3D pose tracking as independent sub-problems that are error-prone when solved in isolation. Furthermore, unlike previous methods, TesseTrack is robust to changes in the number of camera views and achieves very good results even if a single view is available at inference time. Quantitative evaluation of 3D pose reconstruction accuracy on standard benchmarks shows significant improvements over the state of the art. Evaluation of multi-person articulated 3D pose tracking in our novel evaluation framework demonstrates the superiority of TesseTrack over strong baselines.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 | Human3.6M | TesseTrack (Monocular) | Average MPJPE (mm) | 44.6 | #39 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | TesseTrack (Monocular) | Multi-View or Monocular | Monocular | #39 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | TesseTrack (Monocular) | Using 2D ground-truth joints | No | #39 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Panoptic | TesseTrack Multi-View (5 views) | Average MPJPE (mm) | 7.3 | #1 of 9 | Archive leaderboard | report |
| 3D Human Pose Estimation | Panoptic | TesseTrack Monocular | Average MPJPE (mm) | 18.9 | #5 of 9 | Archive leaderboard | report |
| 3D Human Pose Tracking | Panoptic | TesseTrack | 3DMOTA | 94.1 | #1 of 1 | Archive leaderboard | report |
| 3D Multi-Person Pose Estimation | Campus | TesseTrack | PCP3D | 97.4 | #1 of 16 | Archive leaderboard | report |
| 3D Multi-Person Pose Estimation | Panoptic | TesseTrack | Average MPJPE (mm) | 7.3 | #1 of 20 | Archive leaderboard | report |
| 3D Multi-Person Pose Estimation | Shelf | TesseTrack (correct) | PCP3D | 97.9 | #6 of 27 | Archive leaderboard | report |
| 3D Pose Estimation | Human3.6M | TesseTrack | Average MPJPE (mm) | 18.7 | #1 of 4 | 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.
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