Research map / 3D vision / Human pose estimation
Beyond Static Features for Temporally Consistent 3D Human Pose and Shape From a Video
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Remove the residual connection between static and temporal features (ablation) | VIBE-style temporal baseline · 3DPW | Accel: 29.2 -> 8.7 | Helped |
| Add PoseForecast to encode past and future frames (ablation) | VIBE-style temporal baseline · 3DPW | Accel: 29.2 -> 24.9; 8.7 -> 7.7 | Helped |
| Exclude the current frame from PoseForecast input (ablation) | TCMR · 3DPW | Accel: 10.3 -> 7.7 | Helped |
| Supervise PoseForecast SMPL parameters with current-frame ground truth (ablation) | TCMR · 3DPW | PA-MPJPE: 55.1 -> 53.9; 54.1 -> 53.9 | Helped |
| Supervise PoseForecast with past and future frame ground truth instead of current-frame ground truth (ablation) | TCMR · 3DPW | Accel: 7.7 -> 8.5 | Hurt |
| Remove PoseForecast SMPL-parameter supervision (ablation) | TCMR · 3DPW | PA-MPJPE: 53.9 -> 55.1 | Hurt |
| Add average filtering post-processing (ablation) | TCMR · 3DPW | PA-MPJPE: 52.7 -> 55.0 | Hurt |
| Reduce the input frame rate from 30 fps to 15 fps (ablation) | TCMR · 3DPW | Accel: 7.1 -> 15.3 | Hurt |
| Use TCMR instead of MEVA | video-based 3D pose and shape estimation · 3DPW | Accel: 11.6 -> 6.8 | Helped |
| Use TCMR instead of MEVA | video-based 3D pose and shape estimation · MPI-INF-3DHP | Accel: 11.1 -> 8.5 | Helped |
| Use TCMR instead of MEVA | video-based 3D pose and shape estimation · Human3.6M | Accel: 15.3 -> 3.9 | Helped |
Closest papers by meaning
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · similarity 0.88)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.88)
- HumanMM: Global Human Motion Recovery from Multi-shot Videos (CVPR 2025 · similarity 0.88)
- Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video (CVPR 2025 · similarity 0.87)
- BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025 · similarity 0.87)
- Semantics-aware Test-time Adaptation for 3D Human Pose Estimation (ICML 2025 · similarity 0.87)
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.