Research map / 3D vision / 3D generation
ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction From Video Priors
Zihao Huang, Tianqi Liu, Zhaoxi Chen, Shaocong Xu, Saining Zhang, Linqi Xiao, Zhiguo Cao, Wei Li (7081), Hao Zhao, Ziwei Liu
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 two-stage decoupled reconstruction instead of joint optimization (ablation) | ArtHOI · HOI interaction | Contact%: 61.45 -> 75.64 | Improved |
| use two-stage decoupled reconstruction instead of joint optimization (ablation) | ArtHOI · HOI interaction | X-CLIP: 0.187 -> 0.244 | Improved |
| use two-stage decoupled reconstruction instead of joint optimization (ablation) | ArtHOI · Articulation | Rot (mean): 12.34 -> 6.71 | Improved |
| add articulation regularization L_a (ablation) | ArtHOI · Articulation | Rot (mean): 15.67 -> 6.71 | Improved |
| add articulation regularization L_a (ablation) | ArtHOI · HOI interaction | Contact%: 68.75 -> 75.64 | Improved |
| add kinematic loss L_k (ablation) | ArtHOI · HOI interaction | Contact%: 59.82 -> 75.64 | Improved |
| add kinematic loss L_k (ablation) | ArtHOI · HOI interaction | Foot Sliding: 0.58 -> 0.31 | Improved |
| add kinematic loss L_k (ablation) | ArtHOI · Articulation | Rot (mean): 6.71 -> 6.71 | No clear effect |
| add smoothness loss L_s (ablation) | ArtHOI · Articulation | Rot (mean): 8.23 -> 6.71 | Improved |
| add smoothness loss L_s (ablation) | ArtHOI · HOI interaction | Contact%: 65.43 -> 75.64 | Improved |
| use ArtHOI instead of ZeroHSI | ArtHOI · HOI interaction | Penetration%: 1.49 -> 0.08 | Improved |
| use ArtHOI instead of 3DADN for articulation | ArtHOI · Articulated dynamics | Rot (mean): 21.17 -> 6.71 | Improved |
Closest papers by meaning
- Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos (NeurIPS 2026 · similarity 0.92)
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.90)
- AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation (ICLR 2025 · similarity 0.89)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.89)
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.88)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.88)
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.
