13762

On learning optimized reaction diffusion processes for effective image restoration

Yunjin Chen, Wei Yu, Thomas Pock
Graz University of Technology
arXiv:1503.05768 [cs.CV], (19 Mar 2015)

@article{chen2015learning,

   title={On learning optimized reaction diffusion processes for effective image restoration},

   author={Chen, Yunjin and Yu, Wei and Pock, Thomas},

   year={2015},

   month={mar},

   archivePrefix={"arXiv"},

   primaryClass={cs.CV}

}

Download Download (PDF)   View View   Source Source   

910

views

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.
Rating: 2.5. From 1 vote.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: