Robust Image Denoising using Kernel Predicting Networks

Cai, Zhilin; Zhang, Yang; Manzi, Marco; Oztireli, Cengiz; Gross, Markus; Aydin, Tunç Ozan

Robust Image Denoising using Kernel Predicting Networks

Files

037-040.pdf (6.88 MB)

rk-sup.pdf (986.67 KB)

Date

2021

Authors

Cai, Zhilin
Zhang, Yang
Manzi, Marco
Oztireli, Cengiz
Gross, Markus
Aydin, Tunç Ozan

Publisher

The Eurographics Association

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.

        @inproceedings{10.2312:egs.20211018
,
booktitle = {Eurographics 2021 - Short Papers
},
editor = {Theisel, Holger and Wimmer, Michael
},
title = {{Robust Image Denoising using Kernel Predicting Networks
}},
author = {Cai, Zhilin and 
Zhang, Yang and 
Manzi, Marco and 
Oztireli, Cengiz and 
Gross, Markus and 
Aydin, Tunç Ozan
},
year = {2021
},
publisher = {The Eurographics Association
},
ISSN = {1017-4656
},
ISBN = {978-3-03868-133-5
},
DOI = {10.2312/egs.20211018
}
}