Measuring and Controlling the Spectral Bias for Self-Supervised Image Denoising

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Wang, Li, Huaqiu, Hu, Xiaowan, Jiang, Tao, Chen, Zikang, Wang, Haoqian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912620767870976
author Zhang, Wang
Li, Huaqiu
Hu, Xiaowan
Jiang, Tao
Chen, Zikang
Wang, Haoqian
author_facet Zhang, Wang
Li, Huaqiu
Hu, Xiaowan
Jiang, Tao
Chen, Zikang
Wang, Haoqian
contents Current self-supervised denoising methods for paired noisy images typically involve mapping one noisy image through the network to the other noisy image. However, after measuring the spectral bias of such methods using our proposed Image Pair Frequency-Band Similarity, it suffers from two practical limitations. Firstly, the high-frequency structural details in images are not preserved well enough. Secondly, during the process of fitting high frequencies, the network learns high-frequency noise from the mapped noisy images. To address these challenges, we introduce a Spectral Controlling network (SCNet) to optimize self-supervised denoising of paired noisy images. First, we propose a selection strategy to choose frequency band components for noisy images, to accelerate the convergence speed of training. Next, we present a parameter optimization method that restricts the learning ability of convolutional kernels to high-frequency noise using the Lipschitz constant, without changing the network structure. Finally, we introduce the Spectral Separation and low-rank Reconstruction module (SSR module), which separates noise and high-frequency details through frequency domain separation and low-rank space reconstruction, to retain the high-frequency structural details of images. Experiments performed on synthetic and real-world datasets verify the effectiveness of SCNet.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00454
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Measuring and Controlling the Spectral Bias for Self-Supervised Image Denoising
Zhang, Wang
Li, Huaqiu
Hu, Xiaowan
Jiang, Tao
Chen, Zikang
Wang, Haoqian
Computer Vision and Pattern Recognition
Artificial Intelligence
Current self-supervised denoising methods for paired noisy images typically involve mapping one noisy image through the network to the other noisy image. However, after measuring the spectral bias of such methods using our proposed Image Pair Frequency-Band Similarity, it suffers from two practical limitations. Firstly, the high-frequency structural details in images are not preserved well enough. Secondly, during the process of fitting high frequencies, the network learns high-frequency noise from the mapped noisy images. To address these challenges, we introduce a Spectral Controlling network (SCNet) to optimize self-supervised denoising of paired noisy images. First, we propose a selection strategy to choose frequency band components for noisy images, to accelerate the convergence speed of training. Next, we present a parameter optimization method that restricts the learning ability of convolutional kernels to high-frequency noise using the Lipschitz constant, without changing the network structure. Finally, we introduce the Spectral Separation and low-rank Reconstruction module (SSR module), which separates noise and high-frequency details through frequency domain separation and low-rank space reconstruction, to retain the high-frequency structural details of images. Experiments performed on synthetic and real-world datasets verify the effectiveness of SCNet.
title Measuring and Controlling the Spectral Bias for Self-Supervised Image Denoising
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.00454