Multi-Scale Memory-Based Video Deblurring

TL;DR

This paper introduces a multi-scale memory-based approach for video deblurring that leverages a memory bank of blurry-sharp feature pairs, bidirectional recurrency, and multi-scale strategies to improve deblurring quality efficiently.

Contribution

It proposes a novel memory branch with bidirectional recurrency and multi-scale strategies to enhance fine-grained video deblurring performance.

Findings

Outperforms state-of-the-art methods in accuracy

Maintains low model complexity and inference time

Effective memory bank design improves deblurring quality

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.