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

• URL: http://arxiv.org/abs/2510.00454v1
• Date: Wed, 01 Oct 2025 03:07:05 GMT
• Title: Measuring and Controlling the Spectral Bias for Self-Supervised Image Denoising
• Authors: Wang Zhang, Huaqiu Li, Xiaowan Hu, Tao Jiang, Zikang Chen, Haoqian Wang,
• Abstract summary: Current self-supervised denoising methods for paired noisy images involve mapping one noisy image through the network to the other noisy image.<n>We introduce a Spectral Controlling network (SCNet) to optimize self-supervised denoising of paired noisy images.<n>Experiments performed on synthetic and real-world datasets verify the effectiveness of SCNet.
• Score: 32.12139370364104
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Principal Component Analysis-Based Terahertz Self-Supervised Denoising and Deblurring Deep Neural Networks [7.9830655821581304]
  Terahertz (THz) systems inherently introduce frequency-dependent degradation effects, resulting in low-frequency blurring and high-frequency noise in amplitude images.<n>We propose a principal component analysis (PCA)-based THz self-supervised denoising and deblurring network (THz-SSDD)<n>The network employs a Recorrupted-to-Recorrupted self-supervised learning strategy to capture the intrinsic features of noise.
  arXiv  Detail & Related papers  (2026-01-17T19:45:01Z)
• Towards Frequency-Adaptive Learning for SAR Despeckling [10.764049665817629]
  We propose a frequency-adaptive heterogeneous despeckling model based on a divide-and-conquer architecture.<n>Inspired by their differing noise characteristics, we design specialized sub-networks for different frequency components.<n>For high-frequency sub-bands rich in edges and textures, we introduce an enhanced U-Net with deformable convolutions for noise suppression and enhanced features.
  arXiv  Detail & Related papers  (2025-11-08T07:08:22Z)
• Learning Multi-scale Spatial-frequency Features for Image Denoising [58.883244886588336]
  We propose a novel multi-scale adaptive dual-domain network (MADNet) for image denoising.<n>We use image pyramid inputs to restore noise-free results from low-resolution images.<n>In order to realize the interaction of high-frequency and low-frequency information, we design an adaptive spatial-frequency learning unit.
  arXiv  Detail & Related papers  (2025-06-19T13:28:09Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• Frequency-Adaptive Pan-Sharpening with Mixture of Experts [22.28680499480492]
  We propose a novel Frequency Adaptive Mixture of Experts (FAME) learning framework for pan-sharpening. Our method performs the best against other state-of-the-art ones and comprises a strong generalization ability for real-world scenes.
  arXiv  Detail & Related papers  (2024-01-04T08:58:25Z)
• Hierarchical Disentangled Representation for Invertible Image Denoising and Beyond [14.432771193620702]
  Inspired by a latent observation that noise tends to appear in the high-frequency part of the image, we propose a fully invertible denoising method. We decompose the noisy image into clean low-frequency and hybrid high-frequency parts with an invertible transformation. In this way, denoising is made tractable by inversely merging noiseless low and high-frequency parts.
  arXiv  Detail & Related papers  (2023-01-31T01:24:34Z)
• Thunder: Thumbnail based Fast Lightweight Image Denoising Network [92.9631117239565]
  A textbfThumbtextbfnail based textbfDtextbfenoising Netwotextbfrk dubbed Thunder is proposed.
  arXiv  Detail & Related papers  (2022-05-24T06:38:46Z)
• Exploring Inter-frequency Guidance of Image for Lightweight Gaussian Denoising [1.52292571922932]
  We propose a novel network architecture denoted as IGNet, in order to refine the frequency bands from low to high in a progressive manner. With this design, more inter-frequency prior and information are utilized, thus the model size can be lightened while still perserves competitive results.
  arXiv  Detail & Related papers  (2021-12-22T10:35:53Z)
• Unsupervised Image Denoising with Frequency Domain Knowledge [2.834895018689047]
  Supervised learning-based methods yield robust denoising results, yet they are inherently limited by the need for large-scale datasets. In this study we propose a frequency-sensitive unsupervised denoising method. Results using natural and synthetic datasets indicate that our unsupervised learning method augmented with frequency information achieves state-of-the-art denoising performance.
  arXiv  Detail & Related papers  (2021-11-29T07:41:32Z)
• Wavelet-Based Network For High Dynamic Range Imaging [64.66969585951207]
  Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. In this work, we propose a novel frequency-guided end-to-end deep neural network (FNet) to conduct HDR fusion in the frequency domain, and Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details.
  arXiv  Detail & Related papers  (2021-08-03T12:26:33Z)
• Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images [98.82804259905478]
  We present Neighbor2Neighbor to train an effective image denoising model with only noisy images. In detail, input and target used to train a network are images sub-sampled from the same noisy image. A denoising network is trained on sub-sampled training pairs generated in the first stage, with a proposed regularizer as additional loss for better performance.
  arXiv  Detail & Related papers  (2021-01-08T02:03:25Z)
• Flexible Image Denoising with Multi-layer Conditional Feature Modulation [56.018132592622706]
  We present a novel flexible image enoising network (CFMNet) by equipping an U-Net backbone with conditional feature modulation (CFM) modules. In comparison to channel-wise shifting only in the first layer, CFMNet can make better use of noise level information by deploying multiple layers of CFM. Our CFMNet is effective in exploiting noise level information for flexible non-blind denoising, and performs favorably against the existing deep image denoising methods in terms of both quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2020-06-24T06:00:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.