Research map / 3D vision / 3D generation
F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions
Jie Yang, Xuesong Niu, Nan Jiang, Ruimao Zhang, Siyuan Huang
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 offset regression to generation (ablation) | F-HOI · Semantic-HOI Generation | Chamfer distance (averaged): 27.9 -> 22.9 | Improved |
| add offset regression (ablation) | F-HOI · Semantic-HOI Understanding | BLEU-4: 26.91 -> 26.78 | No clear effect |
| add image-to-pose alignment pretraining on COCO (ablation) | F-HOI · Semantic-HOI Generation | Chamfer distance (averaged): 32.7 -> 24.8 | Improved |
| add image-to-pose alignment pretraining on COCO (ablation) | F-HOI · Semantic-HOI Reconstruction | Chamfer distance (averaged): 33.9 -> 25.8 | Improved |
| add text-to-pose alignment pretraining on PoseScript (ablation) | F-HOI · Semantic-HOI Understanding | BLEU-4: 23.76 -> 26.78 | Improved |
| add text-to-pose alignment pretraining on PoseScript (ablation) | F-HOI · Semantic-HOI Reasoning | BLEU-4: 23.43 -> 25.56 | Improved |
| train jointly on all four tasks instead of a single task (ablation) | F-HOI · Semantic-HOI Understanding | BLEU-4: 24.67 -> 26.78 | Improved |
| train jointly on all four tasks instead of a single task (ablation) | F-HOI · Semantic-HOI Generation | Chamfer distance (averaged): 24.0 -> 22.9 | Improved |
| use F-HOI (MLLM with HOI-pose projectors and mesh encoder) instead of finetuned LLaVA baseline | Semantic-HOI generation · Semantic-HOI Generation | Chamfer distance (averaged): 44.4 -> 22.9 | Improved |
Closest papers by meaning
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.89)
- CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024 · similarity 0.89)
- HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models (CVPR 2025 · similarity 0.89)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.89)
- Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection (CVPR 2024 · similarity 0.89)
- Open-World Human-Object Interaction Detection via Multi-modal Prompts (CVPR 2024 · 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.
