Papers › SEFD: Learning to Distill Complex Pose and Occlusion
SEFD: Learning to Distill Complex Pose and Occlusion
ChangHee Yang, Kyeongbo Kong, SungJun Min, Dongyoon Wee, Ho-Deok Jang, Geonho Cha, SukJu Kang
This paper addresses the problem of three-dimensional (3D) human mesh estimation in complex poses and occluded situations. Although many improvements have been made in 3D human mesh estimation using the two-dimensional (2D) pose with occlusion between humans, occlusion from complex poses and other objects remains a consistent problem. Therefore, we propose the novel Skinned Multi-Person Linear (SMPL) Edge Feature Distillation (SEFD) that demonstrates robustness to complex poses and occlusions, without increasing the number of parameters compared to the baseline model. The model generates an SMPL overlapping edge similar to the ground truth that contains target person boundary and occlusion information, performing subsequent feature distillation in a simple edge map. We also perform experiments on various benchmarks and exhibit fidelity both qualitatively and quantitatively. Extensive experiments prove that our method outperforms the state-of-the-art method by 2.8% in MPJPE and 1.9% in MPVPE on a benchmark 3DPW dataset in the presence of domain gap. Also, our method is superior in 3DPW-OCC, 3DPW-PC, RH-Dataset, OCHuman, CrowdPose, and LSP dataset in which occlusion, complex pose, and domain gap exist. The code and occlusion & complex pose annotation will be available at https: //anonymous.4open.science/r/SEFD-B7F8/
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 |
|---|---|---|---|---|---|---|---|
| 2D Human Pose Estimation | OCHuman | SEFD | Test AP | 44.1 | #2 of 11 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | SEFD_GT | MPJPE | 64.75 | #12 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | SEFD_GT | MPVPE | 78.36 | #12 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | SEFD_GT | PA-MPJPE | 43.79 | #12 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | SEFD | MPJPE | 77.37 | #39 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | SEFD | MPVPE | 92.60 | #39 of 119 | Archive leaderboard | report |
| 3D Human Pose Estimation | 3DPW | SEFD | PA-MPJPE | 49.39 | #39 of 119 | 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