AI Paper Atlas

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

TPAMI 2025 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 69 citations (OpenAlex)

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 changedWhereMeasuredEffect
use regressed twist angles instead of random twist (ablation)HybrIK (GT joints) · AGORA valvertex error: 67.3 -> 10.0Improved
use regressed twist angles instead of zero twist (ablation)HybrIK (GT joints) · AGORA valvertex error: 12.1 -> 10.0Improved
use adaptive update instead of naive HybrIK under noisy joints (+-30 mm) (ablation)HybrIK body-only · AGORA valMPJPE 24 joints: 100.2 -> 67.5Improved
use backward-updated HybrIK-X instead of Adaptive HybrIK for hand joints (+-30 mm) (ablation)whole-body IK · AGORA valhand MPJPE: 47.8 -> 40.4Improved
use backward-updated HybrIK-X instead of Adaptive HybrIK for body joints (+-30 mm) (ablation)whole-body IK · AGORA valbody MPJPE: 59.0 -> 57.6No clear effect
apply HybrIK correction to predicted joints (ablation)predicted pose · AGORA valMPJPE 24 joints: 73.1 -> 66.3Improved
apply SMPLify instead of HybrIK on predicted pose (ablation)predicted pose · AGORA valMPJPE 24 joints: 73.1 -> 100.1Hurt
apply HybrIK correction to predicted joints (ablation)predicted pose · Human3.6MMPJPE 24 joints: 50.9 -> 48.1Improved
apply HybrIK correction to predicted joints (ablation)predicted pose · 3DPWMPJPE 24 joints: 78.9 -> 74.8Improved
replace heatmap with RLE regression for 3D keypoints (ablation)HybrIK-X · AGORA val with truncationMPJPE: 99.8 -> 82.7Improved
use 1D deviation RLE- instead of original RLE (ablation)HybrIK-X · AGORA val with truncationMPJPE: 82.7 -> 80.4Improved
use 1D deviation RLE- instead of original RLE (ablation)HybrIK-X · AGORA testMPJPE: 109.7 -> 107.6Improved

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.

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy