Research map / 3D vision / Human pose estimation
ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss
Jiaying Ying, Heming Du, Kaihao Zhang, Sean M. Tweedy, Xin Yu
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 ResiHMR residual-limb modules to SMPLify-X | SMPLify-X · LDPose-LimbLoss Evaluation Dataset (255 images) | 2D MPJPE body keypoints (px): 47.67 px to 41.77 px | Improved |
| add ResiHMR residual-limb modules to SMPLify-X | SMPLify-X · LDPose-LimbLoss Evaluation Dataset (255 images) | 2D MPJPE residual-limb endpoints (px): 129.59 px to 98.36 px | Improved |
| add ResiHMR residual-limb modules to SMPLify-X | SMPLify-X · LDPose-LimbLoss Evaluation Dataset (255 images) | 2D MPJPE intact keypoints (px): 41.32 px to 37.40 px | Improved |
| add ResiHMR residual-limb modules to SMPLify-X | SMPLify-X · LDPose-LimbLoss Evaluation Dataset (255 images) | mIoU: 0.662 to 0.703 | Improved |
| add ResiHMR residual-limb modules to HSMR | HSMR · LDPose-LimbLoss Evaluation Dataset (255 images) | 2D MPJPE body keypoints (px): 28.27 px to 24.75 px | Improved |
| add ResiHMR residual-limb modules to HSMR | HSMR · LDPose-LimbLoss Evaluation Dataset (255 images) | 2D MPJPE residual-limb endpoints (px): 73.61 px to 23.19 px | Improved |
| add ResiHMR residual-limb modules to HSMR | HSMR · LDPose-LimbLoss Evaluation Dataset (255 images) | 2D MPJPE intact keypoints (px): 24.56 vs. 24.87 px | No clear effect |
| add ResiHMR residual-limb modules to HSMR | HSMR · LDPose-LimbLoss Evaluation Dataset (255 images) | mIoU: 0.705 to 0.741 | Improved |
| compare ResiHMR (HSMR) mIoU against CameraHMR | ResiHMR (HSMR) · LDPose-LimbLoss Evaluation Dataset (255 images) | mIoU: 0.741 vs 0.752 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PromptHMR — PromptHMR: Promptable Human Mesh Recovery (CVPR 2025) · better on 3 of 4 shared results
- TokenHMR — TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024) · better on 4 of 4 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
- AJAHR: Amputated Joint Aware 3D Human Mesh Recovery (ICCV 2025 · similarity 0.89)
- Hierarchical Kinematic Human Mesh Recovery (ECCV 2020 · similarity 0.88)
- End-to-End Recovery of Human Shape and Pose (CVPR 2018 · similarity 0.88)
- SAM 3D Body: Robust Full-Body Human Mesh Recovery (CVPR 2026 · similarity 0.87)
- FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · similarity 0.87)
- Reconstructing Humans with a Biomechanically Accurate Skeleton (CVPR 2025 · similarity 0.85)
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.
