metadata
license: apache-2.0
FineGrasp: Towards Robust Grasping for Delicate Objects
Grasp performance in GraspNet-1Billion dataset.
| Method | ckpt | Camera | Seen (AP) | Similar (AP) | Novel (AP) | Average (AP) |
|---|---|---|---|---|---|---|
| FineGrasp | finegrasp_wo_sim.pth | Realsense | 71.67 | 62.83 | 27.40 | 53.97 |
| FineGrasp + CD | finegrasp_wo_sim.pth | Realsense | 73.71 | 64.56 | 28.14 | 55.47 |
| FineGrasp + Simulation Data | finegrasp_sim.pth | Realsense | 70.21 | 61.98 | 26.18 | 52.79 |
We also provide a grasp-based baseline for Challenge Cup, please refer to this code
Notice: finegrasp_sim.pth is trained for Challenge Cup RoboTwin simulation benchmark.
Citation
@article{du2025finegrasp,
title={FineGrasp: Towards Robust Grasping for Delicate Objects},
author={Du, Yun and Zhao, Mengao and Lin, Tianwei and Jin, Yiwei and Huang, Chaodong and Su, Zhizhong},
journal={arXiv preprint arXiv:2507.05978},
year={2025}
}