Research map / 3D vision / 3D generation
TaxoGrasp: Taxonomy-Guided Human Grasp Synthesis with Sparse Contact Constraint
Haitian Liu, Yin Wang, Zhiying Leng, Kanglei Zhou, Yan Wang, Frederick W. B. Li, Xiaohui Liang
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 Cognition taxonomy inference (instead of random taxonomy label) (ablation) | TaxoGrasp · HOGraspNet | cFID: 8.590 -> 1.714 | Improved |
| add Cognition taxonomy inference (instead of random taxonomy label) (ablation) | TaxoGrasp · HOGraspNet | TDD: 1.009 -> 0.223 | Improved |
| add Cognition taxonomy inference (instead of random taxonomy label) (ablation) | TaxoGrasp · HOGraspNet | penetration volume (PV): 1.938 -> 1.265 | Improved |
| add diffusion Instantiation (instead of fixed template pose) (ablation) | TaxoGrasp · HOGraspNet | cFID: 3.135 -> 1.714 | Improved |
| add diffusion Instantiation (instead of fixed template pose) (ablation) | TaxoGrasp · HOGraspNet | contact area (CA): 113.2 -> 120.1 | Improved |
| add diffusion Instantiation (instead of fixed template pose) (ablation) | TaxoGrasp · HOGraspNet | max penetration depth (PD max): 0.238 -> 0.340 | Hurt |
| add Grounding refinement (ablation) | TaxoGrasp · HOGraspNet | penetration volume (PV): 3.588 -> 1.265 | Improved |
| add Grounding refinement (ablation) | TaxoGrasp · HOGraspNet | contact area (CA): 107.3 -> 120.1 | Improved |
| add Grounding refinement (ablation) | TaxoGrasp · HOGraspNet | cFID: 2.625 -> 1.714 | Improved |
| add Grounding refinement (ablation) | TaxoGrasp · HOGraspNet | simulation displacement (SIM): 11.78 -> 10.72 | Improved |
| use TaxoGrasp instead of RegionGrasp | RegionGrasp · HOGraspNet | cFID: 2.968 -> 1.714 | Improved |
| use TaxoGrasp instead of RegionGrasp | RegionGrasp · HOGraspNet | penetration volume (PV): 4.309 -> 1.265 | Improved |
Closest papers by meaning
- CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning (ECCV 2026 · similarity 0.91)
- Grasp’D: Differentiable Contact-Rich Grasp Synthesis for Multi-Fingered Hands (ECCV 2022 · similarity 0.89)
- D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions (CVPR 2022 · similarity 0.88)
- RAGG: Retrieval-Augmented Grasp Generation Model (AAAI 2025 · similarity 0.88)
- Grasp as You Say: Language-guided Dexterous Grasp Generation (NeurIPS 2024 · similarity 0.87)
- Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges (NeurIPS 2025 · similarity 0.86)
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.
