AI Paper Atlas

Research map / 3D vision / Human pose estimation

HuCollisionField: Resolving Self-Collisions via Neural Fields for Human Prediction

Zhengyuan Li, Zeyun Deng, Yifan Shen, Liang-Yan Gui, Miaolan Xie, Joseph Campbell, Xifeng Gao, Kui Wu, Zherong Pan, Aniket Bera

ECCV 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture

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 PoseShield instead of COAPcollision resolution · HwCsuccess rate: 0.446 -> 0.958Improved
add weighted distance (WD) in pose space (ablation)PoseShield · HwCmean vertex distance: 0.067 -> 0.059Improved
add weighted distance (WD) in pose space (ablation)PoseShield · HwCsuccess rate: 0.960 -> 0.958Mixed
add weighted distance (WD) in pose space (ablation)PoseShield · PROXsuccess rate: 0.850 -> 0.800Hurt
use LTD instead of Lgrad (ablation)PoseShield · HwCsuccess rate: 0.862 -> 0.958Improved
use LTD instead of Lgrad (ablation)PoseShield · PROXsuccess rate: 0.520 -> 0.800Improved
add Lgrad on top of LTD (ablation)PoseShield · HwCsuccess rate: 0.958 -> 0.870Hurt
add Eikonal gradient terms (Lgrad or LTD) (ablation)PoseShield · HwCsuccess rate: 0.068 -> 0.958Improved
add Eikonal gradient terms (Lgrad or LTD) (ablation)PoseShield · PROXsuccess rate: 0.050 -> 0.800Improved
increase constraint margin Cl (ablation)PoseShield · HwCSCC vs MVDMixed
use neural field instead of classifier probability constraintlatent-space optimization · HwCsuccess rate: 0.056 -> 0.958Improved

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