Research map / 3D vision / Human pose estimation
Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
Junuk Cha, Muhammad Saqlain, GeonU Kim, Mingyu Shin, Seungryul Baek
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 inverse kinematics from 3D skeleton (vs skeleton only, no refiner) (ablation) | Ours · 3DPW | MPJPE: 71.8 -> 67.3 | Improved |
| add inverse kinematics from 3D skeleton (ablation) | Ours · 3DPW | PA-MPJPE: 42.5 -> 39.3 | Improved |
| add relation-aware Transformer refiner (ablation) | Ours · 3DPW | MPJPE: 67.3 -> 66.0 | Improved |
| add relation-aware Transformer refiner (ablation) | Ours · 3DPW | PA-MPJPE: 39.3 -> 39.0 | Improved |
| add relation-aware Transformer refiner (ablation) | Ours · 3DPW | MVE: 77.5 -> 76.3 | Improved |
| do not add positional embedding (ablation) | Ours · 3DPW | MPJPE: 68.3 -> 66.0 | Improved |
| add masking of input patches (ablation) | Ours · 3DPW | MPJPE: 67.1 -> 66.0 | Improved |
| add masking of input patches (ablation) | Ours · 3DPW | PA-MPJPE: 39.0 -> 39.0 | No clear effect |
| raise refiner input persons N from 1 to 3 (ablation) | Ours · 3DPW | MPJPE: 66.9 -> 66.0 | Improved |
| raise refiner input persons N from 3 to 4 (ablation) | Ours · 3DPW | MPJPE: 66.0 -> 66.6 | Hurt |
| raise refiner input persons N from 2 to 3 (ablation) | Ours · 3DPW | MVE: 76.7 -> 76.3 | 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.
- SPEC — SPEC: Seeing People in the Wild With an Estimated Camera (ICCV 2021) · better on 2 of 2 shared results
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
- Direct Multi-view Multi-person 3D Pose Estimation (NeurIPS 2021 · similarity 0.89)
- Explicit Occlusion Reasoning for Multi-Person 3D Human Pose Estimation (ECCV 2022 · similarity 0.88)
- Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery (ICCV 2021 · similarity 0.88)
- Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints (CVPR 2018 · similarity 0.88)
- HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation (ECCV 2020 · similarity 0.88)
- 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.
