One-Pot Multi-Frame Denoising

• URL: http://arxiv.org/abs/2302.11544v1
• Date: Sat, 18 Feb 2023 09:32:59 GMT
• Title: One-Pot Multi-Frame Denoising
• Authors: Lujia Jin, Shi Zhao, Lei Zhu, Qian Chen, Yanye Lu
• Abstract summary: We propose an unsupervised learning strategy named one-pot denoising (OPD) for multi-frame images. OPD executes mutual supervision among all of the multiple frames, which gives learning more diversity of supervision. In practice, our experiments demonstrate that OPD behaves as the SOTA unsupervised denoising method.
• Score: 11.372794025435955
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The performance of learning-based denoising largely depends on clean supervision. However, it is difficult to obtain clean images in many scenes. On the contrary, the capture of multiple noisy frames for the same field of view is available and often natural in real life. Therefore, it is necessary to avoid the restriction of clean labels and make full use of noisy data for model training. So we propose an unsupervised learning strategy named one-pot denoising (OPD) for multi-frame images. OPD is the first proposed unsupervised multi-frame denoising (MFD) method. Different from the traditional supervision schemes including both supervised Noise2Clean (N2C) and unsupervised Noise2Noise (N2N), OPD executes mutual supervision among all of the multiple frames, which gives learning more diversity of supervision and allows models to mine deeper into the correlation among frames. N2N has also been proved to be actually a simplified case of the proposed OPD. From the perspectives of data allocation and loss function, two specific implementations, random coupling (RC) and alienation loss (AL), are respectively provided to accomplish OPD during model training. In practice, our experiments demonstrate that OPD behaves as the SOTA unsupervised denoising method and is comparable to supervised N2C methods for synthetic Gaussian and Poisson noise, and real-world optical coherence tomography (OCT) speckle noise.

Related papers

• Filter2Noise: Interpretable Self-Supervised Single-Image Denoising for Low-Dose CT with Attention-Guided Bilateral Filtering [3.788107003189284]
  We propose an interpretable self-supervised single-image denoising framework -- Filter2Noise (F2N) Our approach introduces an Attention-Guided Bilateral Filter that adapted to each noisy input through a lightweight module. On the Mayo Clinic 2016 low-dose CT dataset, F2N outperforms the leading self-supervised single-image method (ZS-N2N) by 4.5 dB9 PSNR.
  arXiv  Detail & Related papers  (2025-04-18T07:15:27Z)
• Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising [26.67217493971613]
  Existing self-supervised image denoising paradigms rely heavily on information-lossy operations. We propose a novel self-supervised single image denoising paradigm, Positive2Negative, to break the information-lossy barrier. Our paradigm achieves state-of-the-art performance in self-supervised single image denoising with significant speed improvements.
  arXiv  Detail & Related papers  (2024-12-21T03:25:01Z)
• Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising [19.08732222562782]
  Supervised deep learning has become the method of choice for image denoising. We show that, contrary to popular belief, denoising networks specialized in the removal of Gaussian noise can be efficiently leveraged in favor of real-world image denoising.
  arXiv  Detail & Related papers  (2024-07-24T16:23:46Z)
• Random Sub-Samples Generation for Self-Supervised Real Image Denoising [9.459398471988724]
  We propose a novel self-supervised real image denoising framework named Sampling Difference As Perturbation (SDAP) We find that adding an appropriate perturbation to the training images can effectively improve the performance of BSN. The results show that it significantly outperforms other state-of-the-art self-supervised denoising methods on real-world datasets.
  arXiv  Detail & Related papers  (2023-07-31T16:39:35Z)
• Enhancing convolutional neural network generalizability via low-rank weight approximation [6.763245393373041]
  Sufficient denoising is often an important first step for image processing. Deep neural networks (DNNs) have been widely used for image denoising. We introduce a new self-supervised framework for image denoising based on the Tucker low-rank tensor approximation.
  arXiv  Detail & Related papers  (2022-09-26T14:11:05Z)
• Zero-shot Blind Image Denoising via Implicit Neural Representations [77.79032012459243]
  We propose an alternative denoising strategy that leverages the architectural inductive bias of implicit neural representations (INRs) We show that our method outperforms existing zero-shot denoising methods under an extensive set of low-noise or real-noise scenarios.
  arXiv  Detail & Related papers  (2022-04-05T12:46:36Z)
• CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image [53.76319163746699]
  We propose a novel and powerful self-supervised denoising method called CVF-SID. CVF-SID can disentangle a clean image and noise maps from the input by leveraging various self-supervised loss terms. It achieves state-of-the-art self-supervised image denoising performance and is comparable to other existing approaches.
  arXiv  Detail & Related papers  (2022-03-24T11:59:28Z)
• IDR: Self-Supervised Image Denoising via Iterative Data Refinement [66.5510583957863]
  We present a practical unsupervised image denoising method to achieve state-of-the-art denoising performance. Our method only requires single noisy images and a noise model, which is easily accessible in practical raw image denoising. To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes.
  arXiv  Detail & Related papers  (2021-11-29T07:22:53Z)
• 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)
• Suppression of Correlated Noise with Similarity-based Unsupervised Deep Learning [7.61850613267116]
  Noise2Sim is an unsupervised deep denoising approach that works in a nonlocal nonlinear fashion to suppress correlated noises. Nosie2Sim recovers features from noisy low-dose and photon-counting CT images as effectively as or even better than supervised learning methods.
  arXiv  Detail & Related papers  (2020-11-06T14:31:08Z)
• Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising [54.730707387866076]
  We introduce Noise2Same, a novel self-supervised denoising framework. In particular, Noise2Same requires neither J-invariance nor extra information about the noise model. Our results show that our Noise2Same remarkably outperforms previous self-supervised denoising methods.
  arXiv  Detail & Related papers  (2020-10-22T18:12:26Z)
• 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)

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.