Blind Image Deblurring Using Multi-Task Convolutional Neural Network and Spatially Variant Recurrent Neural Network
- 1 January 2023
- conference paper
- Published by Keldysh Institute of Applied Mathematics
Abstract
We present a novel method of blind image deblurring, capable of handling spatially variant blur caused by various reasons such as camera shake and object motions. Due to the spatially variant nature of the complex blur, our deblurring method includes both spatially variant and spatially invariant components. Namely, we utilize hybrid neural network consisting of a convolutional neural network and a spatially variant recurrent neural network trained in end-to-end manner. Recurrent neural network is used as a deconvolution operator performed on feature maps extracted from the input image by the convolutional neural network, while per-pixel weights of the recurrent neural network are also produced by the same convolutional neural network, making it solve both tasks at the same time. Such hybrid and multi-tasking design allows us to achieve both low computational complexity and high deblurring quality. Quantitative and qualitative evaluations on the widely used GoPro dataset demonstrate that the proposed method provides a good trade-off in terms of complexity and quality against state-of-the-art algorithms.Keywords
This publication has 15 references indexed in Scilit:
- Adversarial Spatio-Temporal Learning for Video DeblurringIEEE Transactions on Image Processing, 2018
- Scale-Recurrent Network for Deep Image Deblurring2018
- DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks2018
- Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks2018
- Reblur2Deblur: Deblurring videos via self-supervised learning2018
- From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur2017
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring2017
- Deep Video Deblurring for Hand-Held Cameras2017
- Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network2016
- Learning a convolutional neural network for non-uniform motion blur removal2015