Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding
Preprint
Abstract
Single-image super-resolution (SR) and multi-frame SR are two ways to super resolve low-resolution images. Single-Image SR generally handles each image independently, but ignores the temporal information implied in continuing frames. Multi-frame SR is able to model the temporal dependency via capturing motion information. However, it relies on neighbouring frames which are not always available in the real world. Meanwhile, slight camera shake easily causes heavy motion blur on long-distance-shot low-resolution images. To address these problems, a Blind Motion Deblurring Super-Reslution Networks, BMDSRNet, is proposed to learn dynamic spatio-temporal information from single static motion-blurred images. Motion-blurred images are the accumulation over time during the exposure of cameras, while the proposed BMDSRNet learns the reverse process and uses three-streams to learn Bidirectional spatio-temporal information based on well designed reconstruction loss functions to recover clean high-resolution images. Extensive experiments demonstrate that the proposed BMDSRNet outperforms recent state-of-the-art methods, and has the ability to simultaneously deal with image deblurring and SR.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic PriorInternational Journal of Computer Vision, 2022
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- To Learn Image Super-Resolution, Use a GAN to Learn How to Do Image Degradation First2018
- A Neural Approach to Blind Motion Deblurring2016
- Deeply-Recursive Convolutional Network for Image Super-Resolution2016
- Learning a convolutional neural network for non-uniform motion blur removal2015
- Learning a Deep Convolutional Network for Image Super-Resolution2014
- Image super-resolution using gradient profile prior2008
- New edge-directed interpolationIEEE Transactions on Image Processing, 2001
- Total variation blind deconvolutionIEEE Transactions on Image Processing, 1998