On learning optimized reaction diffusion processes for effective image restoration
Yunjin Chen, Wei Bo Yu, Thomas Pock · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2015
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.
Cited by 323 works. doi:10.1109/cvpr.2015.7299163 Open-access PDF
Authors
References
- Gradient-based learning applied to document recognition
- Scale-space and edge detection using anisotropic diffusion
- On the limited memory BFGS method for large scale optimization
- Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
- Offline Arabic Handwriting Recognition with Multidimensional Recurrent Neural Networks
- Anisotropic diffusion in image processing
- Natural Image Denoising with Convolutional Networks
- Non-local sparse models for image restoration
- Prior learning and Gibbs reaction-diffusion
- From learning models of natural image patches to whole image restoration