Toward Convolutional Blind Denoising of Real Photographs

Guo, Shi; Yan, Zifei; Zhang, Kai; Zuo, Wangmeng; Zhang, Lei

doi:10.48550/arxiv.1807.04686

Cited by 19 publications

(39 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By interactively setting relatively higher noise level, FFDNet [6] can deal with more complex noise. CBDNet [7] further utilizes a noise estimation subnetwork, so that the entire network could achieve endto-end blind denoising. Yu et al [8] propose a multi-path CNN named Path-Restore, which could dynamically select an appropriate route for each image region, especially for the varied noise distribution of a real noisy image.…”

Section: Introductionmentioning

confidence: 99%

Pyramid Real Image Denoising Network

Zhao

Jiang

Men

et al. 2019

2019 IEEE Visual Communications and Image Processing (VCIP)

View full text Add to dashboard Cite

While deep Convolutional Neural Networks (CNNs) have shown extraordinary capability of modelling specific noise and denoising, they still perform poorly on real-world noisy images. The main reason is that the real-world noise is more sophisticated and diverse. To tackle the issue of blind denoising, in this paper, we propose a novel pyramid real image denoising network (PRIDNet), which contains three stages. First, the noise estimation stage uses channel attention mechanism to recalibrate the channel importance of input noise. Second, at the multi-scale denoising stage, pyramid pooling is utilized to extract multi-scale features. Third, the stage of feature fusion adopts a kernel selecting operation to adaptively fuse multi-scale features. Experiments on two datasets of real noisy photographs demonstrate that our approach can achieve competitive performance in comparison with state-of-the-art denoisers in terms of both quantitative measure and visual perception quality. Code is available at https://github.com/491506870/PRIDNet.

show abstract

Section: Introductionmentioning

confidence: 99%

Pyramid Real Image Denoising Network

Zhao

Jiang

Men

et al. 2019

2019 IEEE Visual Communications and Image Processing (VCIP)

View full text Add to dashboard Cite

show abstract

“…The shot noise is dynamically affected by light intensity, while N t is usually stable and measurable. As reported in previous researches (Foi et al 2008;Guo et al 2018), Gaussian/Poisson noise are usually adopted to approximate the thermal/shot noise. Assuming that the VIS signal are independent with the NIR signal, the shot noise…”

Section: Imaging In Both Daytime and Nighttimementioning

confidence: 99%

An Integrated Enhancement Solution for 24-hour Colorful Imaging

Zheng

et al. 2020

Preprint

View full text Add to dashboard Cite

The current industry practice for 24-hour outdoor imaging is to use a silicon camera supplemented with near-infrared (NIR) illumination. This will result in color images with poor contrast at daytime and absence of chrominance at nighttime. For this dilemma, all existing solutions try to capture RGB and NIR images separately. However, they need additional hardware support and suffer from various drawbacks, including short service life, high price, specific usage scenario, etc. In this paper, we propose a novel and integrated enhancement solution that produces clear color images, whether at abundant sunlight daytime or extremely low-light nighttime. Our key idea is to separate the VIS and NIR information from mixed signals, and enhance the VIS signal adaptively with the NIR signal as assistance. To this end, we build an optical system to collect a new VIS-NIR-MIX dataset and present a physically meaningful image processing algorithm based on CNN. Extensive experiments show outstanding results, which demonstrate the effectiveness of our solution.

show abstract

“…FFD-Net [32] non-blindly removes additive white Gaussian noise (AWGN) with a tunable noise level map and is one of the most efficient networks. CBDNet [13] can blindly remove actual noises by estimating the noise levels through a noise estimation subnetwork. Nevertheless, flexibility and computational efficiency of these networks are still inadequate because they feature a single denoising network.…”

Section: Discriminative Learning Based Denoisingmentioning

confidence: 99%

“…Nevertheless, their recovering performances are limited because noise models are usually intro-duced manually. In contrast, discriminative learning based methods learn the underlying mapping between clean images and noisy ones by exploiting large modeling capacity of deep convolutional neural networks (CNNs) [31,32,13]. Although learning based methods demonstrate advanced performances if the evaluation data resembles the training data used, they are often outperformed by image prior based methods when tested on actual noisy images [25,1].…”

Section: Introductionmentioning

confidence: 99%

Fast and Flexible Image Blind Denoising via Competition of Experts

Maeda

2019

Preprint

View full text Add to dashboard Cite

Fast and flexible processing are two essential requirements for a number of practical applications of image denoising. Current state-of-the-art methods, however, still require either high computational cost or limited scopes of the target. We introduce an efficient ensemble network trained via a competition of expert networks, as an application for image blind denoising. We realize automatic division of unlabeled noisy datasets into clusters respectively optimized to enhance denoising performance. The architecture is scalable, can be extended to deal with diverse noise sources/levels without increasing the computation time. Taking advantage of this method, we save up to approximately 90% of computational cost without sacrifice of the denoising performance compared to single network models with identical architectures. We also compare the proposed method with several existing algorithms and observe significant outperformance over prior arts in terms of computational efficiency.

show abstract

Toward Convolutional Blind Denoising of Real Photographs

Cited by 19 publications

References 50 publications

Pyramid Real Image Denoising Network

Pyramid Real Image Denoising Network

An Integrated Enhancement Solution for 24-hour Colorful Imaging

Fast and Flexible Image Blind Denoising via Competition of Experts

Contact Info

Product

Resources

About