LAN: Learning to Adapt Noise for Image Denoising

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Changjin, Kim, Tae Hyun, Baik, Sungyong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916523460788224
author Kim, Changjin
Kim, Tae Hyun
Baik, Sungyong
author_facet Kim, Changjin
Kim, Tae Hyun
Baik, Sungyong
contents Removing noise from images, a.k.a image denoising, can be a very challenging task since the type and amount of noise can greatly vary for each image due to many factors including a camera model and capturing environments. While there have been striking improvements in image denoising with the emergence of advanced deep learning architectures and real-world datasets, recent denoising networks struggle to maintain performance on images with noise that has not been seen during training. One typical approach to address the challenge would be to adapt a denoising network to new noise distribution. Instead, in this work, we shift our focus to adapting the input noise itself, rather than adapting a network. Thus, we keep a pretrained network frozen, and adapt an input noise to capture the fine-grained deviations. As such, we propose a new denoising algorithm, dubbed Learning-to-Adapt-Noise (LAN), where a learnable noise offset is directly added to a given noisy image to bring a given input noise closer towards the noise distribution a denoising network is trained to handle. Consequently, the proposed framework exhibits performance improvement on images with unseen noise, displaying the potential of the proposed research direction. The code is available at https://github.com/chjinny/LAN
format Preprint
id arxiv_https___arxiv_org_abs_2412_10651
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LAN: Learning to Adapt Noise for Image Denoising
Kim, Changjin
Kim, Tae Hyun
Baik, Sungyong
Computer Vision and Pattern Recognition
Artificial Intelligence
Removing noise from images, a.k.a image denoising, can be a very challenging task since the type and amount of noise can greatly vary for each image due to many factors including a camera model and capturing environments. While there have been striking improvements in image denoising with the emergence of advanced deep learning architectures and real-world datasets, recent denoising networks struggle to maintain performance on images with noise that has not been seen during training. One typical approach to address the challenge would be to adapt a denoising network to new noise distribution. Instead, in this work, we shift our focus to adapting the input noise itself, rather than adapting a network. Thus, we keep a pretrained network frozen, and adapt an input noise to capture the fine-grained deviations. As such, we propose a new denoising algorithm, dubbed Learning-to-Adapt-Noise (LAN), where a learnable noise offset is directly added to a given noisy image to bring a given input noise closer towards the noise distribution a denoising network is trained to handle. Consequently, the proposed framework exhibits performance improvement on images with unseen noise, displaying the potential of the proposed research direction. The code is available at https://github.com/chjinny/LAN
title LAN: Learning to Adapt Noise for Image Denoising
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.10651