English

Multi-Scale Memory-Based Video Deblurring

Image and Video Processing 2022-04-08 v1 Computer Vision and Pattern Recognition

Abstract

Video deblurring has achieved remarkable progress thanks to the success of deep neural networks. Most methods solve for the deblurring end-to-end with limited information propagation from the video sequence. However, different frame regions exhibit different characteristics and should be provided with corresponding relevant information. To achieve fine-grained deblurring, we designed a memory branch to memorize the blurry-sharp feature pairs in the memory bank, thus providing useful information for the blurry query input. To enrich the memory of our memory bank, we further designed a bidirectional recurrency and multi-scale strategy based on the memory bank. Experimental results demonstrate that our model outperforms other state-of-the-art methods while keeping the model complexity and inference time low. The code is available at https://github.com/jibo27/MemDeblur.

Keywords

Cite

@article{arxiv.2204.02977,
  title  = {Multi-Scale Memory-Based Video Deblurring},
  author = {Bo Ji and Angela Yao},
  journal= {arXiv preprint arXiv:2204.02977},
  year   = {2022}
}

Comments

Accepted by CVPR 2022