Research map / 3D vision / 3D generation
Task-Oriented Human Grasp Synthesis via Context- and Task-Aware Diffusers
An-Lun Liu, Yu-Wei Chao, Yi-Ting Chen
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 task-aware instead of object-centric contact maps (ablation) | Ours · Placing | Task Score: 0.439 -> 0.570 | Improved |
| use task-aware instead of object-centric contact maps (ablation) | Ours · Stacking | Task Score: 0.561 -> 0.684 | Improved |
| use task-aware instead of object-centric contact maps (ablation) | Ours · Shelving | Task Score: 0.485 -> 0.552 | Improved |
| use ground-truth instead of predicted task-aware contact maps (ablation) | Ours · Placing | Task Score: 0.570 -> 0.660 | Improved |
| use GraspDiffuser instead of Modified GraspTTA after ContactDiffuser (ablation) | Ours · Placing | Task Score: 0.416 -> 0.563 | Improved |
| use GraspDiffuser instead of Modified GraspTTA after ContactDiffuser (ablation) | Ours · Shelving | Task Score: 0.434 -> 0.550 | Improved |
| use GraspDiffuser instead of Modified GraspTTA after ContactDiffuser (ablation) | Ours · Stacking | Task Score: 0.689 -> 0.687 | No clear effect |
| use ContactDiffuser instead of ContactCVAE (ablation) | Ours · Shelving | Task Score: 0.469 -> 0.550 | Improved |
| use ContactDiffuser instead of ContactCVAE (ablation) | Ours · Placing | Task Score: 0.549 -> 0.563 | Improved |
| use ContactDiffuser instead of ContactCVAE (ablation) | Ours · Stacking | Task Score: 0.690 -> 0.687 | No clear effect |
| use task-aware contact maps with M-GraspTTA on Stacking versus the full method | M-GraspTTA · Stacking | Task Score: 0.694 vs 0.684 | Mixed |
Closest papers by meaning
- Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation (NeurIPS 2025 · similarity 0.91)
- D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions (CVPR 2022 · similarity 0.89)
- RAGG: Retrieval-Augmented Grasp Generation Model (AAAI 2025 · similarity 0.89)
- DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model (AAAI 2025 · similarity 0.88)
- GEARS: Local Geometry-aware Hand-object Interaction Synthesis (CVPR 2024 · similarity 0.88)
- G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis (CVPR 2024 · 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.
