While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs. The main reason is that their learned models are easy to overfit on the simplified AWGN model which deviates severely from the complicated real-world noise model. In order to improve the generalization ability of deep CNN denoisers, we suggest training a convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs. On the one hand, both signal-dependent noise and in-camera signal processing pipeline is considered to synthesize realistic noisy images. On the other hand, real-world noisy photographs and their nearly noise-free counterparts are also included to train our CBDNet. To further provide an interactive strategy to rectify denoising result conveniently, a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Extensive experimental results on three datasets of real-world noisy pho- tographs clearly demonstrate the superior performance of CBDNet over state-of-the-arts in terms of quantitative met- rics and visual quality. The code has been made available at https://github.com/GuoShi28/CBDNet.

/pdf/toward-convolutional-blind-denoising-of-real-photographs-3jfqjtgn26.pdf

Toward Convolutional Blind Denoising of Real Photographs

The field of image denoising is currently dominated by discriminative deep learning methods that are trained on pairs of noisy input and clean target images. Recently it has been shown that such methods can also be trained without clean targets. Instead, independent pairs of noisy images can be used, in an approach known as Noise2Noise (N2N). Here, we introduce Noise2Void (N2V), a training scheme that takes this idea one step further. It does not require noisy image pairs, nor clean target images. Consequently, N2V allows us to train directly on the body of data to be denoised and can therefore be applied when other methods cannot. Especially interesting is the application to biomedical image data, where the acquisition of training targets, clean or noisy, is frequently not possible. We compare the performance of N2V to approaches that have either clean target images and/or noisy image pairs available. Intuitively, N2V cannot be expected to outperform methods that have more information available during training. Still, we observe that the denoising performance of Noise2Void drops in moderation and compares favorably to training-free denoising methods.

/pdf/noise2void-learning-denoising-from-single-noisy-images-s87icsmhf5.pdf

Noise2Void - Learning Denoising From Single Noisy Images

Deep learning on image denoising: An overview.

Image denoising using deep CNN with batch renormalization.

In last few years, supervised deep learning has emerged as one powerful tool for image denoising, which trains a denoising network over an external dataset of noisy/clean image pairs. However, the requirement on a high-quality training dataset limits the broad applicability of the denoising networks. Recently, there have been a few works that allow training a denoising network on the set of external noisy images only. Taking one step further, this paper proposes a self-supervised learning method which only uses the input noisy image itself for training. In the proposed method, the network is trained with dropout on the pairs of Bernoulli-sampled instances of the input image, and the result is estimated by averaging the predictions generated from multiple instances of the trained model with dropout. The experiments show that the proposed method not only significantly outperforms existing single-image learning or non-learning methods, but also is competitive to the denoising networks trained on external datasets.

/pdf/self2self-with-dropout-learning-self-supervised-denoising-3k0poybk1o.pdf

Self2Self With Dropout: Learning Self-Supervised Denoising From Single Image

In this paper, we consider a typical image blind denoising problem, which is to remove unknown noise from noisy images. As we all know, discriminative learning based methods, such as DnCNN, can achieve state-of-the-art denoising results, but they are not applicable to this problem due to the lack of paired training data. To tackle the barrier, we propose a novel two-step framework. First, a Generative Adversarial Network (GAN) is trained to estimate the noise distribution over the input noisy images and to generate noise samples. Second, the noise patches sampled from the first step are utilized to construct a paired training dataset, which is used, in turn, to train a deep Convolutional Neural Network (CNN) for denoising. Extensive experiments have been done to demonstrate the superiority of our approach in image blind denoising.

/pdf/image-blind-denoising-with-generative-adversarial-network-3iuvpetrsp.pdf

Image Blind Denoising with Generative Adversarial Network Based Noise Modeling

The invention discloses an image denoising method. The method comprises steps: an average block set of a to-be-denoised image is acquired; a corresponding mean value is subtracted from each average block in the average block set to obtain a noise block set; a first noise image in the noise block set is acquired; noise modeling is carried out on the noise block set according to a generative adversarial network to obtain a generator capable of generating the same kind of noise as the to-be-denoised image; a second noise image is acquired according to the generator; according to a noise-free image, the first noise image and the second noise image, a training set is constructed; according to the training set and a discriminative learning method, an image denoising network model is trained; andthe to-be-denoised image is inputted to the image denoising network model to acquire an image after denoising. The invention also provides an image denoising device, equipment and a storage medium. the denoising effects on unknown real noise in real life can be enhanced and the denoising efficiency is improved.

Chen Jiawei

Papers

Image Blind Denoising with Generative Adversarial Network Based Noise Modeling

Image denoising method, device, equipment and storage medium