dc.contributor.author | Cai, Zhilin | en_US |
dc.contributor.author | Zhang, Yang | en_US |
dc.contributor.author | Manzi, Marco | en_US |
dc.contributor.author | Oztireli, Cengiz | en_US |
dc.contributor.author | Gross, Markus | en_US |
dc.contributor.author | Aydin, Tunç Ozan | en_US |
dc.contributor.editor | Theisel, Holger and Wimmer, Michael | en_US |
dc.date.accessioned | 2021-04-09T18:20:28Z | |
dc.date.available | 2021-04-09T18:20:28Z | |
dc.date.issued | 2021 | |
dc.identifier.isbn | 978-3-03868-133-5 | |
dc.identifier.issn | 1017-4656 | |
dc.identifier.uri | https://doi.org/10.2312/egs.20211018 | |
dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/egs20211018 | |
dc.description.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. | en_US |
dc.publisher | The Eurographics Association | en_US |
dc.subject | Computing methodologies | |
dc.subject | Image processing | |
dc.title | Robust Image Denoising using Kernel Predicting Networks | en_US |
dc.description.seriesinformation | Eurographics 2021 - Short Papers | |
dc.description.sectionheaders | Imaging and Video | |
dc.identifier.doi | 10.2312/egs.20211018 | |
dc.identifier.pages | 37-40 | |