Research map / Detection and segmentation / Open-set and few-shot detection
Target-Referenced Reactive Grasping for Dynamic Objects
Jirong Liu, Ruo Zhang, Hao-Shu Fang, Minghao Gou, Hongjie Fang, Chenxi Wang, Sheng Xu, Hengxu Yan, Cewu Lu
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 memory-augmented refinement to grasp correspondence tracking (ablation) | Target-referenced reactive grasping · GraspNet-1Billion | MGTA: -0.32 -> 0.84; -0.30 -> 0.85; -0.39 -> 0.78 | Improved |
| Add memory-augmented refinement to grasp correspondence tracking (ablation) | Target-referenced reactive grasping · Moving GraspNet | MGTA: -0.43 -> 0.52 | Improved |
| Increase detected grasp count from M=512 to M=1024 (ablation) | Target-referenced reactive grasping · GraspNet-1Billion | MGTA: 0.80 -> 0.84; 0.80 -> 0.85; 0.75 -> 0.78 | Improved |
| Increase detected grasp count from M=1024 to M=2048 (ablation) | Target-referenced reactive grasping · GraspNet-1Billion | MGTA: 0.84 -> 0.85; 0.85 -> 0.86; 0.78 -> 0.79 | Improved |
| Increase detected grasp count from M=512 to M=1024 (ablation) | Target-referenced reactive grasping · Moving GraspNet | MGTA: 0.47 -> 0.52 | Improved |
| Increase detected grasp count from M=1024 to M=2048 (ablation) | Target-referenced reactive grasping · Moving GraspNet | MGTA: 0.52 -> 0.54 | Improved |
| Add global scene features to grasp representations (ablation) | Grasp correspondence network · Similar-object scenes, object IDs 7,7,8,8 | correspondence switches: 5 -> 1 | Improved |
| Add global scene features to grasp representations (ablation) | Grasp correspondence network · Similar-object scenes, object IDs 1,17,17 | correspondence switches: 4 -> 0 | Improved |
| Track grasps with target-referenced correspondence and refinement rather than Bundle Track | Target-referenced reactive grasping · Moving GraspNet | MGTA: 0.37 -> 0.52 | Improved |
| Track grasps with target-referenced correspondence and refinement rather than Bundle Track | Target-referenced reactive grasping · GraspNet-1Billion seen objects | MGTA: 0.74 -> 0.84 | Improved |
Closest papers by meaning
- Graspness Discovery in Clutters for Fast and Accurate Grasp Detection (ICCV 2021 · similarity 0.88)
- Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation (NeurIPS 2025 · similarity 0.86)
- Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge (CVPR 2024 · similarity 0.86)
- Active Perception for Grasp Detection via Neural Graspness Field (NeurIPS 2024 · similarity 0.86)
- ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping (CVPR 2025 · similarity 0.86)
- Language-driven Grasp Detection (CVPR 2024 · similarity 0.85)
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.
