A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising

Nam, Seonghyeon; Hwang, Youngbae; Matsushita, Yasuyuki; Kim, Seon Joo

doi:10.1109/cvpr.2016.186

Cited by 210 publications

(244 citation statements)

References 22 publications

Supporting

Mentioning

244

Contrasting

Order By: Relevance

“…In this work, we use only raw-RGB images as they directly represent the noise distribution of the underlying cameras. We avoid using sRGB images as rendering image into sRGB space tends to significantly change the noise distribution [25]. We arrange the data as approximately 500, 000 image patches of size 64 × 64 pixels.…”

Section: Methodsmentioning

confidence: 99%

Noise Flow: Noise Modeling With Conditional Normalizing Flows

Abdelhamed

Brubaker

Brown

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

158

129

View full text Add to dashboard Cite

Modeling and synthesizing image noise is an important aspect in many computer vision applications. The long-standing additive white Gaussian and heteroscedastic (signal-dependent) noise models widely used in the literature provide only a coarse approximation of real sensor noise. This paper introduces Noise Flow, a powerful and accurate noise model based on recent normalizing flow architectures. Noise Flow combines well-established basic parametric noise models (e.g., signal-dependent noise) with the flexibility and expressiveness of normalizing flow networks. The result is a single, comprehensive, compact noise model containing fewer than 2500 parameters yet able to represent multiple cameras and gain factors. Noise Flow dramatically outperforms existing noise models, with 0.42 nats/pixel improvement over the camera-calibrated noise level functions, which translates to 52% improvement in the likelihood of sampled noise. Noise Flow represents the first serious attempt to go beyond simple parametric models to one that leverages the power of deep learning and datadriven noise distributions.

show abstract

Section: Methodsmentioning

confidence: 99%

Noise Flow: Noise Modeling With Conditional Normalizing Flows

Abdelhamed

Brubaker

Brown

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

158

129

View full text Add to dashboard Cite

show abstract

“…Datasets and Results. We evaluate the proposed NLH on two commonly used real-world image denoising datasets, i.e., the Cross-Channel (CC) dataset [37] and the Darmstadt Noise Dataset (DND) [64].…”

Section: Results On Real-world Noisy Imagesmentioning

confidence: 99%

“…To answer this question, we compute the average pixel-wise distances (APDs, the distance apportioned to each pixel) of non-local similar pixels and patches on the CC dataset [37]. From Table VI, we can see that, on 15 mean images and 15 noisy images (normalized into [0, 1]), the APDs of pixel-level NSS are smaller than those of patch-level NSS.…”

Section: Is Pixel-level Nss More Accurate Than Patch-level Nss?mentioning

confidence: 99%

NLH: A Blind Pixel-Level Non-Local Method for Real-World Image Denoising

Hou

Liu

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Non-local self similarity (NSS) is a powerful prior of natural images for image denoising. Most of existing denoising methods employ similar patches, which is a patch-level NSS prior. In this paper, we take one step forward by introducing a pixellevel NSS prior, i.e., searching similar pixels across a non-local region. This is motivated by the fact that finding closely similar pixels is more feasible than similar patches in natural images, which can be used to enhance image denoising performance. With the introduced pixel-level NSS prior, we propose an accurate noise level estimation method, and then develop a blind image denoising method based on the lifting Haar transform and Wiener filtering techniques. Experiments on benchmark datasets demonstrate that, the proposed method achieves much better performance than state-of-the-art methods on real-world image denoising. The code will be released.Index Terms-non-local self similarity, pixel-level similarity, image denoising.

show abstract

“…In order to compare the objective quality fairly, we evaluate the proposed method on Nam datasets compared with NC [3], NI [4], CBM3D [10] and CC [1]. The images were taken by three different cameras and different ISOs.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…The PSNR results of the comparison are listed in Table I. The results of CBM3D and CC are directly copied from [1]. The highest PSNR results are highlighted in bold.…”

Section: Performance Evaluationmentioning

confidence: 99%

A CNN-Based Blind Denoising Method for Endoscopic Images

Zou

Long

Wang

et al. 2019

2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)

View full text Add to dashboard Cite

The quality of images captured by wireless capsule endoscopy (WCE) is key for doctors to diagnose diseases of gastrointestinal (GI) tract. However, there exist many lowquality endoscopic images due to the limited illumination and complex environment in GI tract. After an enhancement process, the severe noise become an unacceptable problem. The noise varies with different cameras, GI tract environments and image enhancement. And the noise model is hard to be obtained. This paper proposes a convolutional blind denoising network for endoscopic images. We apply Deep Image Prior (DIP) method to reconstruct a clean image iteratively using a noisy image without a specific noise model and ground truth. Then we design a blind image quality assessment network based on MobileNet to estimate the quality of the reconstructed images. The estimated quality is used to stop the iterative operation in DIP method. The number of iterations is reduced about 36% by using transfer learning in our DIP process. Experimental results on endoscopic images and real-world noisy images demonstrate the superiority of our proposed method over the state-of-the-art methods in terms of visual quality and quantitative metrics. Keywords-Wireless capsule endoscopy, blind denoising, image quality assessment, convolutional neural network

show abstract

A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising

Cited by 210 publications

References 22 publications

Noise Flow: Noise Modeling With Conditional Normalizing Flows

Noise Flow: Noise Modeling With Conditional Normalizing Flows

NLH: A Blind Pixel-Level Non-Local Method for Real-World Image Denoising

A CNN-Based Blind Denoising Method for Endoscopic Images

Contact Info

Product

Resources

About