Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
- 19 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 4600-4613
Abstract
In the past decade, deep neural networks have revolutionized image denoising in achieving significant accuracy improvements by learning on datasets composed of noisy/clean image pairs. However, this strategy is extremely dependent on training data quality, which is a well-established weakness. To alleviate the requirement to learn image priors externally, single-image ( a.k.a ., self-supervised or zero-shot) methods perform denoising solely based the analysis of the input noisy image without external dictionary or training dataset. This work investigates the effectiveness of linear combinations of patches for denoising under this constraint. Although conceptually very simple, we show that linear combinations of patches are enough to achieve state-of-the-art performance. The proposed parametric approach relies on quadratic risk approximation via multiple pilot images to guide the estimation of the combination weights. Experiments on images corrupted artificially with Gaussian noise as well as on real-world noisy images demonstrate that our method is on par with the very best single-image denoisers, outperforming the recent neural network-based techniques, while being much faster and fully interpretable.Keywords
Funding Information
- Bpifrance Agency through the LiChIE Contract
- Inria Rennes Computing Grid Facilities
- France-BioImaging Infrastructure through the “Investments for the Future” (ANR-10-INBS-04-07)
This publication has 42 references indexed in Scilit:
- Practical Blind Image Denoising via Swin-Conv-UNet and Data SynthesisMachine Intelligence Research, 2023
- A fast blind zero-shot denoiserNature Machine Intelligence, 2022
- A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising2018
- Benchmarking Denoising Algorithms with Real Photographs2017
- Non-local Color Image Denoising with Convolutional Neural Networks2017
- Single image super-resolution from transformed self-exemplars2015
- Weighted Nuclear Norm Minimization with Application to Image Denoising2014
- Secrets of image denoising cuisineActa Numerica, 2012
- The Elements of Statistical Learning2009
- Image Processing and Data Analysis1998