Opendenoising: An Extensible Benchmark for Building Comparative Studies of Image Denoisers (original) (raw)

Real-world Noisy Image Denoising: A New Benchmark

Most of previous image denoising methods focus on additive white Gaussian noise (AWGN). However,the real-world noisy image denoising problem with the advancing of the computer vision techiniques. In order to promote the study on this problem while implementing the concurrent real-world image denoising datasets, we construct a new benchmark dataset which contains comprehensive real-world noisy images of different natural scenes. These images are captured by different cameras under different camera settings. We evaluate the different denoising methods on our new dataset as well as previous datasets. Extensive experimental results demonstrate that the recently proposed methods designed specifically for realistic noise removal based on sparse or low rank theories achieve better denoising performance and are more robust than other competing methods, and the newly proposed dataset is more challenging. The constructed dataset of real photographs is publicly available at https://github.com/csjunxu/PolyUDataset for researchers to investigate new real-world image denoising methods. We will add more analysis on the noise statistics in the real photographs of our new dataset in the next version of this article.

A Comparison of Some State of the Art Image Denoising Methods

2007

We briefly describe and compare some recent advances in image denoising. In particular, we discuss three leading denoising algorithms, and describe their similarities and differences in terms of both structure and performance. Following a summary of each of these methods, several examples with various images corrupted with simulated and real noise of different strengths are presented. With the help of these experiments, we are able to identify the strengths and weaknesses of these state of the art methods, as well as seek the way ahead towards a definitive solution to the long-standing problem of image denoising.

State‐of‐art analysis of image denoising methods using convolutional neural networks

IET Image Processing, 2019

Convolutional neural networks (CNNs) are deep neural networks that can be trained on large databases and show outstanding performance on object classification, segmentation, image denoising etc. In the past few years, several image denoising techniques have been developed to improve the quality of an image. The CNN based image denoising models have shown improvement in denoising performance as compared to non-CNN methods like block-matching and three-dimensional (3D) filtering, contemporary wavelet and Markov random field approaches etc. which had remained state-of-the-art for years. This study provides a comprehensive study of state-of-the-art image denoising methods using CNN. The literature associated with different CNNs used for image restoration like residual learning based models (DnCNN-S, DnCNN-B, IDCNN), non-locality reinforced (NN3D), fast and flexible network (FFDNet), deep shrinkage CNN (SCNN), a model for mixed noise reduction, denoising prior driven network (PDNN) are reviewed. DnCNN-S and PDNN remove Gaussian noise of fixed level, whereas DnCNN-B, IDCNN, NN3D and SCNN are used for blind Gaussian denoising. FFDNet is used for spatially variant Gaussian noise. The performance of these CNN models is analysed on BSD-68 and Set-12 datasets. PDNN shows the best result in terms of PSNR for both BSD-68 and Set-12 datasets.

Image Denoising in the Deep Learning Era

Over the last decade, the number of digital images captured per day witnessed a massive explosion. Nevertheless, the visual quality of photographs is often degraded by noise during image acquisition or transmission. With the re-emergence of deep neural networks, the performance of image denoising techniques has been substantially improved in recent years. The objective of this paper is to provide a comprehensive survey of recent advances in image denoising techniques based on deep neural networks. In doing so, we commence with a thorough description of the fundamental preliminaries of the image denoising problem followed by highlighting the benchmark datasets and the widely used metrics for objective assessments. Subsequently, we study the existing deep denoisers in the supervised and unsupervised categories and review the technical specifics of some representative methods within each category. Last but not least, we conclude the analysis by remarking on trends and challenges in the...

NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020

This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results. The challenge is a new version of the previous NTIRE 2019 challenge on real image denoising that was based on the SIDD benchmark. This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+. This challenge has two tracks for quantitatively evaluating image denoising performance in (1) the Bayer-pattern rawRGB and (2) the standard RGB (sRGB) color spaces. Each track ∼250 registered participants. A total of 22 teams, proposing 24 methods, competed in the final phase of the challenge. The proposed methods by the participating teams represent the current state-of-the-art performance in image denoising targeting real noisy images. The newly collected SIDD+ datasets are publicly available at: https://bit.ly/siddplus\_data.

No-reference Image Denoising Quality Assessment

Advances in Computer Vision, 2019

A wide variety of image denoising methods are available now. However, the performance of a denoising algorithm often depends on individual input noisy images as well as its parameter setting. In this paper, we present a noreference image denoising quality assessment method that can be used to select for an input noisy image the right denoising algorithm with the optimal parameter setting. This is a challenging task as no ground truth is available. This paper presents a data-driven approach to learn to predict image denoising quality. Our method is based on the observation that while individual existing quality metrics and denoising models alone cannot robustly rank denoising results, they often complement each other. We accordingly design denoising quality features based on these existing metrics and models and then use Random Forests Regression to aggregate them into a more powerful unified metric. Our experiments on images with various types and levels of noise show that our no-reference denoising quality assessment method significantly outperforms the state-of-the-art quality metrics. This paper also provides a method that leverages our quality assessment method to automatically tune the parameter settings of a denoising algorithm for an input noisy image to produce an optimal denoising result.

Noise2Grad: Extract Image Noise to Denoise

2021

In many image denoising tasks, the difficulty of collecting noisy/clean image pairs limits the application of supervised CNNs. We consider such a case in which paired data and noise statistics are not accessible, but unpaired noisy and clean images are easy to collect. To form the necessary supervision, our strategy is to extract the noise from the noisy image to synthesize new data. To ease the interference of the image background, we use a noise removal module to aid noise extraction. The noise removal module first roughly removes noise from the noisy image, which is equivalent to excluding much background information. A noise approximation module can therefore easily extract a new noise map from the removed noise to match the gradient of the noisy input. This noise map is added to a random clean image to synthesize a new data pair, which is then fed back to the noise removal module to correct the noise removal process. These two modules cooperate to extract noise finely. After co...

RENOIR - A Benchmark Dataset for Real Noise Reduction Evaluation

In this paper we introduce a dataset of uncompressed color images taken with three digital cameras and exhibiting different levels of natural noise due to low-light conditions. For each scene there are on average two low-noise and two high noise images that are aligned at the pixel level both spatially and in intensity. The dataset contains over 100 scenes and more than 400 images, including both RAW formatted images and 8 bit BMP pixel and intensity aligned images. We also introduce a method for estimating the true noise level in each of our images. We use our dataset to analyze three current state of the art denoising algorithms: Active Random Field, BM3D, and Multi-Layer Perceptron. We found that BM3D obtains the best denoising results, however it is the slowest of the three methods with Active Random Field taking only a few seconds and Multi-Later Perceptron and BM3D taking a few minutes to half an hour to denoise a 10 to 18 mega-pixel image.

From Classical to Deep Learning: A Systematic Review of Image Denoising Techniques

JURNAL ILMIAH COMPUTER SCIENCE (JICS), 2024

Image denoising is essential in image processing and computer vision, aimed at removing noise while preserving critical features. This review compares classical methods like Gaussian filtering and wavelet transforms with modern deep learning techniques such as convolutional neural networks (CNNs) and generative adversarial networks (GANs). We conducted a systematic literature review from [start year] to [end year], analyzing studies from IEEE Xplore, PubMed, and Google Scholar. Classical methods are effective for simple noise models but struggle with fine detail preservation. In contrast, deep learning excels in both noise reduction and detail retention, supported by metrics like PSNR and SSIM. Hybrid approaches combining classical and deep learning show promise for balancing performance and computational efficiency. Overall, deep learning leads in handling complex noise patterns and preserving high-detail images. Future research should focus on optimizing deep learning models, exploring unsupervised learning, and extending denoising applications to real-time and large-scale image processing.

Research Project Proposal: Deep Image Denoising

2020

The goal of image restoration is to recover the original, clean image, starting from a corrupted image. Depending on the type of corruption, image restoration tasks can be divided into deblurring, super-resolution, denoising, inpainting, text removal and many others. In particular, image denoising has the goal of estimating the clean image from its observed version corrupted by noise. Modern image denoising lies at the intersection of signal processing, computer science and machine learning. Indeed, recent technological and methodological advances in deep learning have allowed the employment of convolutional neural networks (CNNs) for image restoration purposes. The obvious application for image denoising is to provide to the user a pleasant and clear image by removing as much noise as possible, without losing details. From a technical point of view, a denoised image is an essential prerequisite for more high-level computer vision tasks and complex deep learning pipelines (e.g. auto...