Research map / 3D vision / Human pose estimation
3D Human Pose Estimation via Intuitive Physics
Shashank Tripathi, Lea Müller, Chun-Hao P. Huang, Omid Taheri, Michael J. Black, Dimitrios Tzionas
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 ground and stability losses to HMR | HMR* · RICH | MPJPE: 82.5 -> 79.0 | Improved |
| Add ground and stability losses to HMR | HMR* · RICH | BOS error (%): 62.0 -> 71.2 | Improved |
| Add stability loss alone (ablation) | HMR* · RICH | PAMPJPE: 48.3 -> 47.5 | Improved |
| Add ground loss alone (ablation) | HMR* · RICH | MPJPE: 82.5 -> 80.9 | Improved |
| Add intuitive-physics losses | HMR* · Human3.6M | MPJPE: 61.6 -> 60.6 | Improved |
| Add ground and stability losses | SMPLify-XMC · MoYo | MPJPE: 75.3 -> 71.9 | Improved |
| Add stability loss alone (ablation) | SMPLify-XMC · MoYo | MPJPE: 75.3 -> 88.5 | Hurt |
| Add ground loss alone (ablation) | SMPLify-XMC · MoYo | MPJPE: 75.3 -> 73.3 | Improved |
| Add push loss only (ablation) | HMR* · RICH | MPJPE: 82.5 -> 85.4 | Hurt |
| Add pull loss only (ablation) | HMR* · RICH | MPJPE: 82.5 -> 88.0 | Hurt |
| Use push and pull losses together instead of either alone (ablation) | HMR* · RICH | MPJPE: 85.4 -> 80.9; 88.0 -> 80.9 | Improved |
| Use volume-weighted part-specific mass for COM rather than naive vertex mean (ablation) | SMPL body COM estimation · MoYo | COM error (mm): 264.1 mm -> 53.3 mm | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SPIN — SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition (AAAI 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Trajectory Optimization for Physics-Based Reconstruction of 3D Human Pose From Monocular Video (CVPR 2022 · similarity 0.90)
- Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (ECCV 2016 · similarity 0.89)
- 3D Human Pose Estimation with Muscles (NeurIPS 2025 · similarity 0.89)
- 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data (NeurIPS 2020 · similarity 0.88)
- Holistic 3D Human and Scene Mesh Estimation From Single View Images (CVPR 2021 · similarity 0.87)
- Reconstructing Humans with a Biomechanically Accurate Skeleton (CVPR 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.
