Research map / Detection and segmentation / CNN features
An Economic Framework for 6-DoF Grasp Detection
Xiao-Ming Wu, Jia-Feng Cai, Jian-Jian Jiang, Dian Zheng, Yi-Lin Wei, Wei-Shi Zheng
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 |
|---|---|---|---|
| keep all grasp views per point (economic supervision) instead of one grasp per point (ablation) | vanilla sparse grasp framework · GraspNet-1Billion Kinect | mean AP: 30.34 -> 42.31 | Improved |
| add interactive grasp head (ablation) | EconomicGrasp · GraspNet-1Billion Kinect | mean AP: 42.31 -> 44.14 | Improved |
| add composite score estimation alone (without interactive head) (ablation) | EconomicGrasp · GraspNet-1Billion Kinect | mean AP: 42.31 -> 42.42 | No clear effect |
| add composite score estimation on top of interactive head (ablation) | EconomicGrasp · GraspNet-1Billion Kinect | mean AP: 44.14 -> 44.62 | Improved |
| add selective match loss (ablation) | EconomicGrasp · GraspNet-1Billion Kinect | mean AP: 42.54 -> 44.62 | Improved |
| use composite score estimation at inference instead of argmax of classified score (ablation) | EconomicGrasp · GraspNet-1Billion Kinect | mean AP: 34.98 -> 44.62 | Improved |
| add global interactive attention then local interactive attention to the head (ablation) | EconomicGrasp · GraspNet-1Billion Kinect | mean AP: 42.42 -> 43.49 -> 44.62 | Improved |
| modernize S4G sparse baseline with region grouping (ablation) | S4G-style sparse baseline · GraspNet-1Billion Kinect seen | AP: 18.72 -> 37.38 | Improved |
| replace PointNet++ with 3D convolution backbone in vanilla framework (ablation) | vanilla sparse framework · GraspNet-1Billion Kinect seen | AP: 39.63 -> 43.59 | Improved |
| replace dense supervision (GSNet) with economic supervision framework | GSNet · GraspNet-1Billion Kinect training time | training time (h): 37.8 -> 8.3 | Improved |
| replace GSNet with EconomicGrasp in real-world pick and place | GSNet · Real-world pick and place | success rate: 87.8% -> 92.3% | Improved |
| replace GSNet with EconomicGrasp on bad-case count | GSNet · GraspNet-1Billion seen scenes | scenes with no successful grasp (of 7680): 109/7680 -> 36/7680 | Improved |
Closest papers by meaning
- Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge (CVPR 2024 · similarity 0.87)
- DexFuncGrasp: A Robotic Dexterous Functional Grasp Dataset Constructed from a Cost-Effective Real-Simulation Annotation System (AAAI 2024 · similarity 0.84)
- Active Perception for Grasp Detection via Neural Graspness Field (NeurIPS 2024 · similarity 0.83)
- Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation (NeurIPS 2026 · similarity 0.83)
- Language-driven Grasp Detection (CVPR 2024 · similarity 0.83)
- DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness (CVPR 2025 · similarity 0.83)
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.
