As modern image denoiser networks have grown in size, their reported performance in popular real noise benchmarks such as DND and SIDD have now long outperformed classic non-deep learning denoisers such as Wiener and Wavelet-based methods. In this paper, we propose to revisit the Wiener filter and re-assess its potential performance. We show that carefully considering the implementation of the Wiener filter can yield similar performance to popular networks such as DnCNN.
@article{arxiv.2303.16640,
title = {Pushing The Limits of the Wiener Filter in Image Denoising},
author = {Clément Bled and François Pitié},
journal= {arXiv preprint arXiv:2303.16640},
year = {2023}
}