Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising

• URL: http://arxiv.org/abs/2603.25869v1
• Date: Thu, 26 Mar 2026 19:51:16 GMT
• Title: Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising
• Abstract summary: Self-supervised image denoising methods have traditionally relied on either architectural constraints or specialized loss functions.<n>We present Learning to Recorrupt, a noise distribution-agnostic denoising technique that eliminates the need for knowledge of the noise distribution.
• Score: 27.048126517014875
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised image denoising methods have traditionally relied on either architectural constraints or specialized loss functions that require prior knowledge of the noise distribution to avoid the trivial identity mapping. Among these, approaches such as Noisier2Noise or Recorrupted2Recorrupted, create training pairs by adding synthetic noise to the noisy images. While effective, these recorruption-based approaches require precise knowledge of the noise distribution, which is often not available. We present Learning to Recorrupt (L2R), a noise distribution-agnostic denoising technique that eliminates the need for knowledge of the noise distribution. Our method introduces a learnable monotonic neural network that learns the recorruption process through a min-max saddle-point objective. The proposed method achieves state-of-the-art performance across unconventional and heavy-tailed noise distributions, such as log-gamma, Laplace, and spatially correlated noise, as well as signal-dependent noise models such as Poisson-Gaussian noise.

Related papers

• ENCORE: Efficient Noise Context-Aware Representation for Low-Dose CT Denoising [1.539942973115038]
  deep learning-based denoising has become widely adopted in low-dose CT.<n>Conventional models fail to account for non-stationary and spatially correlated CT noise characteristics.<n>We propose an Efficient Noise COntext-aware REpresentation framework.
  arXiv  Detail & Related papers  (2026-08-11T00:57:39Z)
• IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising [13.724329101670106]
  We conduct image denoising by utilizing dynamically generated kernels via efficient operations.<n>This approach helps prevent overfitting and improves resilience to unseen noise.<n>Despite being trained on single-level Gaussian noise, our compact model excels across diverse noise types and levels.
  arXiv  Detail & Related papers  (2025-08-27T07:58:07Z)
• Blind2Sound: Self-Supervised Image Denoising without Residual Noise [5.192255321684027]
  Self-supervised blind denoising for Poisson-Gaussian noise remains a challenging task. We propose Blind2Sound, a simple yet effective approach to overcome residual noise in denoised images.
  arXiv  Detail & Related papers  (2023-03-09T11:21:59Z)
• CFNet: Conditional Filter Learning with Dynamic Noise Estimation for Real Image Denoising [37.29552796977652]
  This paper considers real noise approximated by heteroscedastic Gaussian/Poisson Gaussian distributions with in-camera signal processing pipelines. We propose a novel conditional filter in which the optimal kernels for different feature positions can be adaptively inferred by local features from the image and the noise map. Also, we bring the thought that alternatively performs noise estimation and non-blind denoising into CNN structure, which continuously updates noise prior to guide the iterative feature denoising.
  arXiv  Detail & Related papers  (2022-11-26T14:28:54Z)
• Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training [50.018580462619425]
  We propose a novel framework, namely Pixel-level Noise-aware Generative Adrial Network (PNGAN) PNGAN employs a pre-trained real denoiser to map the fake and real noisy images into a nearly noise-free solution space. For better noise fitting, we present an efficient architecture Simple Multi-versa-scale Network (SMNet) as the generator.
  arXiv  Detail & Related papers  (2022-04-06T14:09:02Z)
• C2N: Practical Generative Noise Modeling for Real-World Denoising [53.96391787869974]
  We introduce a Clean-to-Noisy image generation framework, namely C2N, to imitate complex real-world noise without using paired examples. We construct the noise generator in C2N accordingly with each component of real-world noise characteristics to express a wide range of noise accurately.
  arXiv  Detail & Related papers  (2022-02-19T05:53:46Z)
• 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)
• Noise2Kernel: Adaptive Self-Supervised Blind Denoising using a Dilated Convolutional Kernel Architecture [3.796436257221662]
  We propose a dilated convolutional network that satisfies an invariant property, allowing efficient kernel-based training without random masking. We also propose an adaptive self-supervision loss to circumvent the requirement of zero-mean constraint, which is specifically effective in removing salt-and-pepper or hybrid noise.
  arXiv  Detail & Related papers  (2020-12-07T12:13:17Z)
• Adaptive noise imitation for image denoising [58.21456707617451]
  We develop a new textbfadaptive noise imitation (ADANI) algorithm that can synthesize noisy data from naturally noisy images. To produce realistic noise, a noise generator takes unpaired noisy/clean images as input, where the noisy image is a guide for noise generation. Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.
  arXiv  Detail & Related papers  (2020-11-30T02:49:36Z)
• Unpaired Learning of Deep Image Denoising [80.34135728841382]
  This paper presents a two-stage scheme by incorporating self-supervised learning and knowledge distillation. For self-supervised learning, we suggest a dilated blind-spot network (D-BSN) to learn denoising solely from real noisy images. Experiments show that our unpaired learning method performs favorably on both synthetic noisy images and real-world noisy photographs.
  arXiv  Detail & Related papers  (2020-08-31T16:22:40Z)
• Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation [52.75909685172843]
  Real-world image noise removal is a long-standing yet very challenging task in computer vision. We propose a novel unified framework to deal with the noise removal and noise generation tasks. Our method learns the joint distribution of the clean-noisy image pairs.
  arXiv  Detail & Related papers  (2020-07-12T09:16:06Z)
• NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis [5.645552640953684]
  This paper proposes a gradual denoising strategy that iteratively detects the dominating noise in an image, and removes it using a tailored denoiser. The method provides an insight on the nature of the encountered noise, and it makes it possible to extend an existing denoiser with new noise nature.
  arXiv  Detail & Related papers  (2020-02-18T11:09:03Z)

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.