Research map / 3D vision / Human pose estimation
HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-Body Mesh Recovery
Jiefeng Li, Siyuan Bian, Chao Xu, Zhicun Chen, Lixin Yang, Cewu Lu
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 |
|---|---|---|---|
| use regressed twist angles instead of random twist (ablation) | HybrIK (GT joints) · AGORA val | vertex error: 67.3 -> 10.0 | Improved |
| use regressed twist angles instead of zero twist (ablation) | HybrIK (GT joints) · AGORA val | vertex error: 12.1 -> 10.0 | Improved |
| use adaptive update instead of naive HybrIK under noisy joints (+-30 mm) (ablation) | HybrIK body-only · AGORA val | MPJPE 24 joints: 100.2 -> 67.5 | Improved |
| use backward-updated HybrIK-X instead of Adaptive HybrIK for hand joints (+-30 mm) (ablation) | whole-body IK · AGORA val | hand MPJPE: 47.8 -> 40.4 | Improved |
| use backward-updated HybrIK-X instead of Adaptive HybrIK for body joints (+-30 mm) (ablation) | whole-body IK · AGORA val | body MPJPE: 59.0 -> 57.6 | No clear effect |
| apply HybrIK correction to predicted joints (ablation) | predicted pose · AGORA val | MPJPE 24 joints: 73.1 -> 66.3 | Improved |
| apply SMPLify instead of HybrIK on predicted pose (ablation) | predicted pose · AGORA val | MPJPE 24 joints: 73.1 -> 100.1 | Hurt |
| apply HybrIK correction to predicted joints (ablation) | predicted pose · Human3.6M | MPJPE 24 joints: 50.9 -> 48.1 | Improved |
| apply HybrIK correction to predicted joints (ablation) | predicted pose · 3DPW | MPJPE 24 joints: 78.9 -> 74.8 | Improved |
| replace heatmap with RLE regression for 3D keypoints (ablation) | HybrIK-X · AGORA val with truncation | MPJPE: 99.8 -> 82.7 | Improved |
| use 1D deviation RLE- instead of original RLE (ablation) | HybrIK-X · AGORA val with truncation | MPJPE: 82.7 -> 80.4 | Improved |
| use 1D deviation RLE- instead of original RLE (ablation) | HybrIK-X · AGORA test | MPJPE: 109.7 -> 107.6 | Improved |
Later papers that compared with this method
2 later accepted papers report HybrIK-X as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation (TPAMI 2025 · better on 2 of 2 shared results)
- Generative Modeling of Shape-Dependent Self-Contact Human Poses (ICCV 2025 · better on 1 of 1 shared result)
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.
- CLIFF — CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation (ECCV 2022) · better on 2 of 2 shared results
- SPIN — SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition (AAAI 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
- HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation (CVPR 2021 · similarity 0.96)
- One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer (CVPR 2023 · similarity 0.89)
- PyMAF-X: Towards Well-Aligned Full-Body Model Regression From Monocular Images (TPAMI 2023 · similarity 0.88)
- SAM 3D Body: Robust Full-Body Human Mesh Recovery (CVPR 2026 · similarity 0.88)
- Reconstructing Humans with a Biomechanically Accurate Skeleton (CVPR 2025 · similarity 0.86)
- AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024 · similarity 0.86)
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.
