Research map / 3D vision / 3D generation
AnchorHOI: Zero-shot Generation of 4D Human-Object Interaction via Anchor-based Prior Distillation
Sisi Dai, Kai Xu
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 anchor NeRF for pose alignment of SMPL-X in interaction composition (ablation) | AnchorHOI · Static HOI ablation | GPT-4V selection (%): 5.88 -> 94.12 | Improved |
| add body anchor keypoints in motion synthesis (ablation) | AnchorHOI · 4D HOI ablation | GPT-4V selection (%): 5.89 -> 76.47 | Improved |
| add contact anchor keypoints in motion synthesis (ablation) | AnchorHOI · 4D HOI ablation | GPT-4V selection (%): 17.65 -> 76.47 | Improved |
| AnchorHOI vs TC4D on 4D generation | AnchorHOI · 4D HOI generation | CLIP semantic score: 0.3017 -> 0.3149 | Improved |
| AnchorHOI vs TC4D on 4D contact (GPT-4V) | AnchorHOI · 4D HOI generation | GPT-4V contact selection (%): 16.67 -> 70.83 | Improved |
| AnchorHOI static vs InterFusion | AnchorHOI · 3D HOI generation | CLIP semantic score: 0.2951 -> 0.3173 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- InterFusion — InterFusion: Text-Driven Generation of 3D Human-Object Interaction (ECCV 2024) · better on 3 of 3 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
- 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 0.88)
- SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios (NeurIPS 2025 · similarity 0.87)
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.87)
- CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024 · similarity 0.87)
- Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos (NeurIPS 2026 · similarity 0.87)
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.
