Multi-Scale Memory-Based Video Deblurring
This work addresses video deblurring for applications like video enhancement, but it is incremental as it builds on existing deep learning approaches with specific architectural improvements.
The paper tackles video deblurring by designing a memory branch to memorize blurry-sharp feature pairs, using bidirectional recurrency and multi-scale strategies, resulting in a model that outperforms state-of-the-art methods with low complexity and inference time.
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.