GraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectors
GraRe is proposed, which estimates grasp quality from candidate attributes, shell-stratified local geometry, and object context, and which shows that improving candidate ranking provides a practical way to enhance frozen 6-DoF grasp detectors.
Ji-Bao Yuan, Yuhui Zhao, Yinzhen Lv et al.
· 0 citations