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

@misc{du2025finegrasp,
    title={FineGrasp: Towards Robust Grasping for Delicate Objects}, 
    author={Yun Du and Mengao Zhao and Tianwei Lin and Yiwei Jin and Chaodong Huang and Zhizhong Su},
    year={2025},
    eprint={2507.05978},
    archivePrefix={arXiv},
    primaryClass={cs.RO},
    url={https://arxiv.org/abs/2507.05978}, 
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including HorizonRobotics/Finegrasp