Research map / 3D vision / 3D generation
Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models
Hyeonwoo Kim, Sookwan Han, Patrick Kwon, Hanbyul Joo
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 Adaptive Mask Inpainting instead of vanilla inpainting for human insertion (ablation) | RealisticVision inpainting · BEHAVE object renderings | RMSE background: 42.23 -> 15.33 | Improved |
| use Adaptive Mask Inpainting instead of vanilla inpainting (ablation) | RealisticVision inpainting · BEHAVE object renderings | mIoU: 0.535 -> 0.706 | Improved |
| use Adaptive Mask Inpainting instead of vanilla inpainting (ablation) | RealisticVision inpainting · BEHAVE object renderings | mIoU occlusion aware: 0.631 -> 0.815 | Improved |
| learn contact with ComA 3D lifting instead of DECO on the same generated 2D HOI images | contact distribution for human · BEHAVE | SIM (%): 21.66 -> 52.82 | Improved |
| learn contact with ComA instead of IAGNet on the same generated 2D HOI images | contact distribution for object · BEHAVE | SIM (%): 66.34 -> 70.55 | Improved |
| use generated 2D HOI images instead of BEHAVE test images as input to baselines | IAGNet · BEHAVE object contact | SIM (%): 63.86 -> 66.34 | Improved |
| use generated 2D HOI images instead of BEHAVE test images as input to baselines | DECO · BEHAVE human contact | SIM (%): 17.39 -> 21.66 | Improved |
Closest papers by meaning
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.90)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.90)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.90)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.90)
- GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency (CVPR 2025 · similarity 0.90)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (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.
