Multi-Scale Memory-Based Video Deblurring
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1909-1918
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
All Related Versions
Funding Information
- National Research Foundation (NRF-NRFFAI1-2019-0001)
This publication has 25 references indexed in Scilit:
- Enhanced Deep Residual Networks for Single Image Super-Resolution2017
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring2017
- Deep Video Deblurring for Hand-Held Cameras2017
- Deep Residual Learning for Image Recognition2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Key-Value Memory Networks for Directly Reading Documents2016
- Dense 3D Reconstruction from Severely Blurred Images Using a Single Moving Camera2013
- Simultaneous localization, mapping and deblurring2011
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Two deterministic half-quadratic regularization algorithms for computed imaging2002