filename     : Zhang22a.pdf
entry        : article
conference   : Eurographics 2021 - Short Papers
pages        : 37-40
year         : 2021
month        : May
title        : Robust Image Denoising using Kernel Predicting Networks
subtitle     :
author       : Zhilin Cai, Yang Zhang, Marco Manzi, Cengiz Oztireli, Markus Gross, Tun{\c{c}} Ozan Aydin}
booktitle    : Computer Graphics Forum
ISSN/ISBN    : 1017-4656
editor       : Computer Graphics Forum, The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd
publisher    : Computer Graphics Forum
publ.place   :
volume       : 40
issue        : 2
language     : English
keywords     : Image Processing
abstract     : We present a new method for designing high quality denoisers that are robust to varying noise characteristics of input images.
Instead of taking a conventional blind denoising approach or relying on explicit noise parameter estimation networks as well as
invertible camera imaging pipeline models, we propose a two-stage model that first processes an input image with a small set of
specialized denoisers, and then passes the resulting intermediate denoised images to a kernel predicting network that estimates
per-pixel denoising kernels. We demonstrate that our approach achieves robustness to noise parameters at a level that exceeds
comparable blind denoisers, while also coming close to state-of-the-art denoising quality for camera sensor noise.