Research map / 3D vision / Human pose estimation
Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users
Yilin Wen, Kechuan Dong, Fumiya Suginaka, Ken Endo, Yusuke Sugano
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 |
|---|---|---|---|
| combine model-based body joints with model-free prosthesis points (hybrid alignment) vs STv2-Pointmap | STv2-Pointmap · RSP3D 2D detection | MPJPE: 159.64 -> 78.35 | Improved |
| hybrid alignment vs STv2-Pointmap on geometry | STv2-Pointmap · RSP3D 2D detection | CD: 277.15 -> 288.44 | Hurt |
| hybrid alignment vs STv2-Pointmap on F@100 | STv2-Pointmap · RSP3D 2D detection | F@100: 45.44 -> 45.61 | Improved |
| point map output instead of tracking | SpatialTrackerV2 · RSP3D 2D detection | CD: 299.59 -> 277.15 | Improved |
| use 2D ground truth instead of 2D detection | STv2-Pointmap · RSP3D | CD: 277.15 -> 238.71 | Improved |
| use 2D ground truth instead of 2D detection | MotionBERT · RSP3D | MPJPE: 115.06 -> 112.41 | Improved |
| bilateral amputation vs unilateral amputation | Hybrid Alignment · RSP3D | MPJPE: 70.35 -> 91.91 | Hurt |
| hybrid alignment on bilateral amputees | STv2-Pointmap · RSP3D bilateral | CD: 294.21 -> 342.22 | Hurt |
| hybrid alignment on unilateral amputees | STv2-Pointmap · RSP3D unilateral | MPJPE-PA: 122.71 -> 50.63 | Improved |
| SAM3D Body vs AJAHR for body joints | AJAHR · RSP3D | MPJPE: 125.06 -> 78.35 | Improved |
Closest papers by meaning
- InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion (ICLR 2026 · similarity 0.89)
- Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens (ICLR 2023 · similarity 0.87)
- ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users (ICCV 2025 · similarity 0.87)
- 3D Human Pose Estimation with Muscles (NeurIPS 2025 · similarity 0.86)
- HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units (AAAI 2025 · similarity 0.85)
- FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions (CVPR 2024 · 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.
