Research map / 3D vision / 3D generation
HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects
Xintao Lv, Liang Xu, Yichao Yan, Xin Jin, Congsheng Xu, Wu Shuwen, Yifan Liu, Lincheng Li, Mengxiao Bi, Wenjun Zeng, Xiaokang Yang
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 mutual interaction module (mutual attention) between human and object branches (ablation) | HIMO-Gen · HIMO 2-objects | R-Precision (Top 3): 0.4710 -> 0.6369 | Improved |
| add object-pairwise distance loss (ablation) | HIMO-Gen · HIMO 2-objects | FID: 2.8694 -> 1.4811 | Improved |
| add object-pairwise distance loss (ablation) | HIMO-Gen · HIMO 2-objects | R-Precision (Top 3): 0.6426 -> 0.6369 | No clear effect |
| generate human and object motion simultaneously instead of consecutively (ablation) | HIMO-Gen · HIMO 2-objects | FID: 8.5024 -> 1.4811 | Improved |
| condition on 10 past frames instead of 1 or 5 (ablation) | HIMO-SegGen · HIMO-SegGen 2-objects | FID: 8.7320 -> 4.2004 | Improved |
| increase conditioning frames from 10 to 20 (ablation) | HIMO-SegGen · HIMO-SegGen 2-objects | FID: 4.2004 -> 5.6749 | Hurt |
| use segmented text prompts with auto-regressive generation (SegGen vs Gen) | HIMO-Gen · HIMO 2-objects | FID: 1.4811 -> 4.2004 | Mixed |
| HIMO-Gen vs baselines on 3-object partition | HIMO-Gen · HIMO 3-objects | FID: 4.5713 -> 4.7712 | Mixed |
Closest papers by meaning
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.91)
- HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment (CVPR 2024 · similarity 0.90)
- Learning to Generate Human-Human-Object Interactions from Textual Descriptions (NeurIPS 2025 · similarity 0.90)
- AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation (ICLR 2025 · similarity 0.90)
- CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024 · similarity 0.90)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.89)
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.
