Research map / 3D vision / Human pose estimation
PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos
Read the paperCheck 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 |
|---|---|---|---|
| add pose calibration to HMR | HMR · Human3.6M | MPVE: 96.1 -> 61.1 | Helped |
| add pose calibration to HMR | HMR · 3DPW | MPVE: 152.7 -> 108.6 | Helped |
| add pose calibration to HMR | HMR · SURREAL | MPVE: 85.1 -> 59.8 | Helped |
| add the non-rigid term to pose calibration (ablation) | PC-HMR · Human3.6M | MPVE: 69.3 -> 61.1 | Helped |
| fine-tune the entire framework after training modules separately (ablation) | PC-HMR · Human3.6M | MPVE: 85.5 -> 61.1 | Helped |
| replace the template mesh with an HMR mesh stream (ablation) | PC-HMR · Human3.6M | MPVE: 125.72 -> 61.1 | Helped |
| use ground-truth 3D pose instead of estimated 3D pose (ablation) | PC-HMR · Human3.6M | MPVE: 61.1 -> 29.9 | Helped |
| add an estimated rotation around each bone (ablation) | PC-HMR · Human3.6M | MPVE: 61.1 -> 61.0 | No clear effect |
| add shape compensation (ablation) | PC-HMR · Human3.6M | MPVE: 61.2 -> 61.1 | Helped |
| use VideoPose3D rather than SemanticGCN as the 2D-to-3D pose lifter (ablation) | parallel PC-HMR with HMR mesh generator and CPN · Human3.6M | MPVE: 79.0 -> 61.1 | Helped |
| use HMR rather than HMMR as the mesh generator with VideoPose3D (ablation) | parallel PC-HMR with CPN · Human3.6M | MPVE: 61.1 -> 61.1 | No clear effect |
Closest papers by meaning
- GenHMR: Generative Human Mesh Recovery (AAAI 2025 · similarity 0.90)
- Reconstructing Humans with a Biomechanically Accurate Skeleton (CVPR 2025 · similarity 0.90)
- PostureHMR: Posture Transformation for 3D Human Mesh Recovery (CVPR 2024 · similarity 0.89)
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · similarity 0.89)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.88)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · 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.