DocumentCode
3672619
Title
On learning optimized reaction diffusion processes for effective image restoration
Author
Yunjin Chen; Wei Yu;Thomas Pock
Author_Institution
Graz University of Technology, Austria
fYear
2015
fDate
6/1/2015 12:00:00 AM
Firstpage
5261
Lastpage
5269
Abstract
For several decades, image restoration remains an active research topic in low-level computer vision and hence new approaches are constantly emerging. However, many recently proposed algorithms achieve state-of-the-art performance only at the expense of very high computation time, which clearly limits their practical relevance. In this work, we propose a simple but effective approach with both high computational efficiency and high restoration quality. We extend conventional nonlinear reaction diffusion models by several parametrized linear filters as well as several parametrized influence functions. We propose to train the parameters of the filters and the influence functions through a loss based approach. Experiments show that our trained nonlinear reaction diffusion models largely benefit from the training of the parameters and finally lead to the best reported performance on common test datasets for image restoration. Due to their structural simplicity, our trained models are highly efficient and are also well-suited for parallel computation on GPUs.
Keywords
"Training","Diffusion processes","Image restoration","Computational modeling","Convolution","Kernel","Joints"
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on
Electronic_ISBN
1063-6919
Type
conf
DOI
10.1109/CVPR.2015.7299163
Filename
7299163
Link To Document