Research map / 3D vision / 3D generation
Toward Human-Like Grasp: Dexterous Grasping via Semantic Representation of Object-Hand
Tianqiang Zhu, Rina Wu, Xiangbo Lin, Yi Sun
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 pre-training on GraspIt! grasp data (ablation) | Functional grasp model · Functional grasp, train objects | Mean DoC (cm): 1.24 -> 0.62 | Improved |
| add pre-training on GraspIt! grasp data (ablation) | Functional grasp model · Functional grasp, train objects | stable grasp rate (QM>0): 65.05% -> 81.73% | Improved |
| add pre-training on GraspIt! grasp data (ablation) | Functional grasp model · Functional grasp, train objects | Mean QM: 0.032 -> 0.081 | Improved |
| add pre-training on GraspIt! grasp data (ablation) | Functional grasp model · Functional grasp, test objects | Mean DoC (cm): 1.73 -> 1.06 | Improved |
| add pre-training on GraspIt! grasp data (ablation) | Functional grasp model · Functional grasp, test objects | stable grasp rate (QM>0): 60.0% -> 80.0% | Improved |
| add pre-training on GraspIt! grasp data (ablation) | Functional grasp model · Functional grasp, test objects | Mean QM: 0.029 -> 0.059 | Improved |
| add repulsion loss to attraction loss (ablation) | Functional grasp model · Qualitative (Fig. 6) | grasp plausibility | Improved |
| add angle loss and self-collision loss after attraction and repulsion (ablation) | Functional grasp model · Qualitative (Fig. 6) | grasp plausibility | Improved |
Closest papers by meaning
- Toward Human-Like Grasp: Functional Grasp by Dexterous Robotic Hand Via Object-Hand Semantic Representation (TPAMI 2023 · similarity 0.97)
- DexFuncGrasp: A Robotic Dexterous Functional Grasp Dataset Constructed from a Cost-Effective Real-Simulation Annotation System (AAAI 2024 · similarity 0.91)
- Grasp as You Say: Language-guided Dexterous Grasp Generation (NeurIPS 2024 · similarity 0.89)
- Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges (NeurIPS 2025 · similarity 0.89)
- DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness (CVPR 2025 · similarity 0.89)
- Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation (NeurIPS 2025 · similarity 0.88)
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.
