Image Denoising: Can Plain Neural Networks Compete with BM3D?

Abstract

Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. The best currently available denoising methods approximate this mapping with cleverly engineered algorithms. In this work we attempt to learn this mapping directly with a plain multi layer perceptron (MLP) applied to image patches. While this has been done before, we will show that by training on large image databases we are able to compete with the current state-of-the-art image denoising methods. Furthermore, our approach is easily adapted to less extensively studied types of noise (by merely exchanging the training data), for which we achieve excellent results as well.

Cite

Text

Burger et al. "Image Denoising: Can Plain Neural Networks Compete with BM3D?." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247952

Markdown

[Burger et al. "Image Denoising: Can Plain Neural Networks Compete with BM3D?." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/burger2012cvpr-image/) doi:10.1109/CVPR.2012.6247952

BibTeX

@inproceedings{burger2012cvpr-image,
  title     = {{Image Denoising: Can Plain Neural Networks Compete with BM3D?}},
  author    = {Burger, Harold Christopher and Schuler, Christian J. and Harmeling, Stefan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {2392-2399},
  doi       = {10.1109/CVPR.2012.6247952},
  url       = {https://mlanthology.org/cvpr/2012/burger2012cvpr-image/}
}