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
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 |
|---|---|---|---|
| add H-GPE object pose estimation (ablation) | PartCHOI baseline · DNA-Rendering and THuman-Sit subset | penetration ratio PR (%): 61.5 -> 10.4 | Improved |
| add H-GPE object pose estimation (ablation) | PartCHOI baseline · DNA-Rendering and THuman-Sit subset | PSNR: 17.25 -> 19.55 | Improved |
| add H-GPE object pose estimation (ablation) | PartCHOI baseline · DNA-Rendering and THuman-Sit subset | LPIPS: 0.1438 -> 0.1001 | Improved |
| add O-GRM to model with PAR (ablation) | PartCHOI · DNA-Rendering and THuman-Sit subset | penetration ratio PR (%): 9.1 -> 4.9 | Improved |
| add O-GRM to model with PAR (ablation) | PartCHOI · DNA-Rendering and THuman-Sit subset | PSNR: 20.10 -> 20.04 | Hurt |
| add PAR to model with O-GRM (ablation) | PartCHOI · DNA-Rendering and THuman-Sit subset | PSNR: 19.49 -> 20.04 | Improved |
| add PAR to model with O-GRM (ablation) | PartCHOI · DNA-Rendering and THuman-Sit subset | penetration ratio PR (%): 6.5 -> 4.9 | Hurt |
| use H-GPE closed-form voxel alignment instead of iterative layout optimization (SDS, depth, M-VRGB) (ablation) | PartCHOI · DNA-Rendering and THuman-Sit subset | layout convergence and pose accuracy | Improved |
| use part-aware PartCHOI pipeline vs LayoutDreamer | LayoutDreamer · Runtime | time: 65min -> 3min | Improved |
| use PartCHOI vs PSHuman | PSHuman · DNA-Rendering and THuman-Sit subset | PSNR: 19.47 -> 20.04 | Improved |
| use PartCHOI vs TRELLIS | TRELLIS · DNA-Rendering and THuman-Sit subset | LPIPS: 0.1513 -> 0.0967 | Improved |
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.
- PSHuman — PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025) · better on 5 of 5 shared results
- MultiGO — MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025) · better on 4 of 4 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
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.89)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.87)
- ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation (CVPR 2025 · similarity 0.87)
- CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024 · similarity 0.87)
- Learning to Generate Human-Human-Object Interactions from Textual Descriptions (NeurIPS 2025 · similarity 0.86)
- Semantic-Aware Human Object Interaction Image Generation (ICML 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.
