Home

Awesome

BlurHand

This repository is an official implementation of the paper "Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding (CVPR 2023)". [arxiv]

alt text

Alt text

<div align="center"> (Left: Blurry input, Right: BlurHandNet output) </div>

BlurHand

You can download our BlurHand dataset in the following link.

Instruction on our dataset is available at here.

BlurHandNet

Please follow the below instructions.

  1. Installation and Dataset preparation.
  2. Training the BlurHandNet (skip the process if you only want to run a pre-trained model).
  3. Testing.

Citation

If our work was helpful for your research, please cite our paper.

@inproceedings{oh2023BlurHand,
  title={Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding},
  author={Oh, Yeounguk and Park, JoonKyu and Kim, Jaeha and Moon, Gyeongsik and Lee, Kyoung Mu},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2023}
}

Acknowledgement

Our code implementaions are motivated from the below codes. We thank the authors for sharing the awesome repositories.

Contact

If you have any question, please email jhkim97s2@gmail.com.