Research map / 3D vision / Human pose estimation
GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Seen | AP: 25.96/27.59 -> 27.56/29.88 | Helped |
| Use the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Unseen | AP: 22.68/24.38 -> 26.11/27.84 | Helped |
| Use the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Novel | AP: 9.23/10.66 -> 10.55/11.51 | Helped |
| Use the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Seen | AP0.8: 33.01/34.21 -> 33.43/36.19 | Helped |
| Use the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Unseen | AP0.8: 29.15/30.84 -> 34.18/33.19 | Mixed |
| Use the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Novel | AP0.8: 9.89/11.24 -> 11.25/12.92 | Helped |
| Use the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Seen | AP0.4: 15.37/17.83 -> 16.95/19.31 | Helped |
| Use the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Unseen | AP0.4: 10.76/12.83 -> 14.23/16.62 | Helped |
| Use the proposed end-to-end grasp network rather than Liang et al. | GraspNet-1Billion benchmark · Novel | AP0.4: 2.74/3.21 -> 3.98/3.56 | Mixed |
| Add classification-based learning rather than directly regressing grasp pose representations (ablation) | Proposed grasp network · Seen (Kinect) | AP: 23.74 -> 29.88 | Helped |
| Add classification-based learning rather than directly regressing grasp pose representations (ablation) | Proposed grasp network · Seen (Kinect) | AP0.8: 33.28 -> 36.19 | Helped |
| Add classification-based learning rather than directly regressing grasp pose representations (ablation) | Proposed grasp network · Seen (Kinect) | AP0.4: 12.15 -> 19.31 | Helped |
Closest papers by meaning
- Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge (CVPR 2024 · similarity 0.88)
- Language-driven Grasp Detection (CVPR 2024 · similarity 0.87)
- Active Perception for Grasp Detection via Neural Graspness Field (NeurIPS 2024 · similarity 0.87)
- Single-View Scene Point Cloud Human Grasp Generation (CVPR 2024 · similarity 0.86)
- ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping (CVPR 2025 · similarity 0.86)
- CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes (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.