Research map / 3D vision / Human pose estimation
RePOSE: 3D Human Pose Estimation via Spatio-Temporal Depth Relational Consistency
Ziming Sun, Yuan Liang, Zejun Ma, Tianle Zhang, Linchao Bao, Guiqing Li, Shengfeng He
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add spatial relational depth ranking loss (ablation) | RePOSE baseline · Human3.6M | MPJPE (mm): 37.9 -> 36.9 | Improved |
| add temporal relational depth ranking loss (ablation) | RePOSE baseline · Human3.6M | MPJPE (mm): 37.9 -> 37.2 | Improved |
| add both spatial and temporal losses (ablation) | RePOSE baseline · Human3.6M | MPJPE (mm): 37.9 -> 36.5 | Improved |
| add both spatial and temporal losses (ablation) | RePOSE baseline · Human3.6M | PA-MPJPE (mm): 32.5 -> 30.7 | Improved |
| fine-tune MotionBERT with the ST relational losses | MotionBERT · Human3.6M | MPJPE (mm): 37.5 -> 36.7 | Improved |
| fine-tune STCFormer with the ST relational losses | STCFormer · Human3.6M | MPJPE (mm): 44.1 -> 43.3 | Improved |
| fine-tune P-STMO-S with the ST relational losses | P-STMO-S · Human3.6M | MPJPE (mm): 46.1 -> 44.7 | Improved |
| RePOSE versus best prior on MPI-INF-3DHP PCK | RePOSE · MPI-INF-3DHP | PCK: 98.7 vs 98.3 | Mixed |
Closest papers by meaning
- RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering (ICCV 2021 · similarity 0.90)
- Occlusion-Aware Networks for 3D Human Pose Estimation in Video (ICCV 2019 · similarity 0.89)
- Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation (CVPR 2021 · similarity 0.89)
- RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation (CVPR 2019 · similarity 0.89)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.88)
- ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
