LAN: Learning to Adapt Noise for Image Denoising

TL;DR

LAN introduces a novel approach to image denoising by adapting the input noise itself with a learnable offset, enabling pretrained networks to better handle unseen noise types without retraining.

Contribution

The paper proposes a new method that adapts input noise rather than the network, improving denoising performance on unseen noise distributions.

Findings

Improved denoising on images with unseen noise.

Maintains performance of pretrained networks without retraining.

Demonstrates effectiveness of noise adaptation approach.

Abstract

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