Research map / 3D vision / 3D generation
AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis
Xiaofei Wu, Yi Zhang, Yumeng Liu, Yuexin Ma, Yujiao Shi, Xuming He
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 DAM instead of ControlNet conditioning (ablation) | AffordGrasp · HO-3D (zero-shot, trained on GRAB) | penetration volume: 16.06 -> 7.38 | Improved |
| use DAM instead of ControlNet conditioning (ablation) | AffordGrasp · OakInk | semantic ACC: 76.94% -> 80.08% | Improved |
| add Distribution Adjustment Module (DAM) (ablation) | AffordGrasp · HO-3D (zero-shot) | penetration volume: 11.21 -> 7.38 | Improved |
| add DAM (ablation) | AffordGrasp · AffordPose (zero-shot) | penetration volume: 12.32 -> 10.36 | Improved |
| add DAM (ablation) | AffordGrasp · OakInk | semantic ACC: 79.11% -> 80.08% | Improved |
| add DAM (ablation) | AffordGrasp · GRAB | semantic ACC: 63.00% -> 62.50% | No clear effect |
| add DAM (ablation) | AffordGrasp · OakInk | cluster size (diversity): 4.07 -> 3.74 | Hurt |
| add object affordance cue (ablation) | AffordGrasp · GRAB | semantic ACC: 55.00% -> 62.50% | Improved |
| add object affordance cue (ablation) | AffordGrasp · GRAB | penetration volume: 4.32 -> 3.06 | Improved |
| add object affordance cue (ablation) | AffordGrasp · OakInk | simulation displacement: 1.22 -> 1.43 | Hurt |
| add object affordance cue (ablation) | AffordGrasp · AffordPose (zero-shot) | semantic ACC: 67.81% -> 72.43% | Improved |
| use DAM single-pass refinement instead of test-time adaptation (inference time) | AffordGrasp · inference efficiency | time (s): 7.09s -> 0.45s | Improved |
Later papers that compared with this method
1 later accepted paper reports AffordGrasp as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Fixed Reality, Diffused Possibility: Disentangling Stochastic and Deterministic Latent for Cluttered Grasping (ECCV 2026 · better on 1 of 1 shared result)
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
- OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model (NeurIPS 2025 · similarity 0.91)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.90)
- LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion. (CVPR 2025 · similarity 0.90)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.89)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.89)
- DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model (AAAI 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.
