Research map / Image generation / Autoregressive and latent generation
Hand-Object Interaction Image Generation
Hezhen Hu, Weilun Wang, Wengang Zhou, Houqiang Li
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 |
|---|---|---|---|
| remove object topology (ablation) | HOGAN · HO3Dv3 | FID: 41.3 -> 47.3 | Hurt |
| remove object topology (ablation) | HOGAN · HO3Dv3 | LPIPS: 0.171 -> 0.183 | Hurt |
| remove hand topology (ablation) | HOGAN · HO3Dv3 | FID: 41.3 -> 47.8 | Hurt |
| remove hand topology (ablation) | HOGAN · HO3Dv3 | LPIPS: 0.171 -> 0.187 | Hurt |
| remove source feature transfer (ablation) | HOGAN · HO3Dv3 | FID: 41.3 -> 46.5 | Hurt |
| remove source feature transfer (ablation) | HOGAN · HO3Dv3 | LPIPS: 0.171 -> 0.181 | Hurt |
| use bilinear instead of attention sampling for source feature transfer (ablation) | HOGAN · HO3Dv3 | FID: 41.3 -> 42.5 | Hurt |
| use bilinear instead of attention sampling for source feature transfer (ablation) | HOGAN · HO3Dv3 | LPIPS: 0.171 -> 0.173 | Hurt |
| remove split-and-combine generation (ablation) | HOGAN · HO3Dv3 | FID: 41.3 -> 44.2 | Hurt |
| remove split-and-combine generation (ablation) | HOGAN · HO3Dv3 | LPIPS: 0.171 -> 0.207 | Hurt |
| train the HOPE backbone with HOGAN-synthesized data | HOPE backbone · HOPE evaluation | hand AUC: 77.2 -> 78.0 | Improved |
| train the HOPE backbone with HOGAN-synthesized data | HOPE backbone · HOPE evaluation | object ADD-0.1D: 67.6 -> 76.8 | Improved |
Closest papers by meaning
- Single-view Image to Novel-view Generation for Hand-Object Interactions (AAAI 2025 · similarity 0.89)
- HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data (CVPR 2024 · similarity 0.89)
- SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios (NeurIPS 2025 · similarity 0.88)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.87)
- Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction (CVPR 2024 · similarity 0.87)
- HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models (CVPR 2025 · 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.
