AI Paper Atlas

Research map / 3D vision / 3D generation

PartCHOI: Part-Aware Guidance for Clothed Human-Object Interaction Generation

Mingwen Shao, Xinyuan Chen, Qiao Zhang, Xiang Lv, lingzhuang meng, Qinglin Zhan, Chang Liu, Chao Dong

ECCV 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation · 0 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
add H-GPE object pose estimation (ablation)PartCHOI baseline · DNA-Rendering and THuman-Sit subsetpenetration ratio PR (%): 61.5 -> 10.4Improved
add H-GPE object pose estimation (ablation)PartCHOI baseline · DNA-Rendering and THuman-Sit subsetPSNR: 17.25 -> 19.55Improved
add H-GPE object pose estimation (ablation)PartCHOI baseline · DNA-Rendering and THuman-Sit subsetLPIPS: 0.1438 -> 0.1001Improved
add O-GRM to model with PAR (ablation)PartCHOI · DNA-Rendering and THuman-Sit subsetpenetration ratio PR (%): 9.1 -> 4.9Improved
add O-GRM to model with PAR (ablation)PartCHOI · DNA-Rendering and THuman-Sit subsetPSNR: 20.10 -> 20.04Hurt
add PAR to model with O-GRM (ablation)PartCHOI · DNA-Rendering and THuman-Sit subsetPSNR: 19.49 -> 20.04Improved
add PAR to model with O-GRM (ablation)PartCHOI · DNA-Rendering and THuman-Sit subsetpenetration ratio PR (%): 6.5 -> 4.9Hurt
use H-GPE closed-form voxel alignment instead of iterative layout optimization (SDS, depth, M-VRGB) (ablation)PartCHOI · DNA-Rendering and THuman-Sit subsetlayout convergence and pose accuracyImproved
use part-aware PartCHOI pipeline vs LayoutDreamerLayoutDreamer · Runtimetime: 65min -> 3minImproved
use PartCHOI vs PSHumanPSHuman · DNA-Rendering and THuman-Sit subsetPSNR: 19.47 -> 20.04Improved
use PartCHOI vs TRELLISTRELLIS · DNA-Rendering and THuman-Sit subsetLPIPS: 0.1513 -> 0.0967Improved

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