Papers › Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation
Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Anirudh Jamkhandi, Pradyumna YM, Varun Jampani, Anirban Chakraborty, R. Venkatesh Babu
Available 3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision. Barring synthetic or in-studio domains, acquiring such supervision for each new target environment is highly inconvenient. To this end, we cast 3D pose learning as a self-supervised adaptation problem that aims to transfer the task knowledge from a labeled source domain to a completely unpaired target. We propose to infer image-to-pose via two explicit mappings viz. image-to-latent and latent-to-pose where the latter is a pre-learned decoder obtained from a prior-enforcing generative adversarial auto-encoder. Next, we introduce relation distillation as a means to align the unpaired cross-modal samples i.e. the unpaired target videos and unpaired 3D pose sequences. To this end, we propose a new set of non-local relations in order to characterize long-range latent pose interactions unlike general contrastive relations where positive couplings are limited to a local neighborhood structure. Further, we provide an objective way to quantify non-localness in order to select the most effective relation set. We evaluate different self-adaptation settings and demonstrate state-of-the-art 3D human pose estimation performance on standard benchmarks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | 3DPW | Non-Local Latent Relation Distillation | PA-MPJPE | 72.1 | #105 of 119 | Archive leaderboard | report |
| Unsupervised 3D Human Pose Estimation | Human3.6M | Non-Local Latent Relation Distillation | MPJPE | 97.8 | #6 of 12 | Archive leaderboard | report |
| Unsupervised 3D Human Pose Estimation | Human3.6M | Non-Local Latent Relation Distillation | PA-MPJPE | 86.2 | #6 of 12 | Archive leaderboard | report |
| Weakly-supervised 3D Human Pose Estimation | Human3.6M | Non-Local Latent Relation Distillation | Average MPJPE (mm) | 57.6 | #8 of 33 | Archive leaderboard | report |
| Weakly-supervised 3D Human Pose Estimation | Human3.6M | Non-Local Latent Relation Distillation | PA-MPJPE | 48.2 | #8 of 33 | 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