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

By Seonghyeon Nam, Youngbae Hwang, Yasuyuki Matsushita, Seon Joo Kim. 2016

278 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, methodology): “To synthesize Gaussian noise, the three-dimensional (3D) zero-mean Gaussian noise model N (0,Σ) [36] with covariance matrix Σ is adopted.”
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising (2017, background): “with zero mean and covariance matrix in the RGB color space [38].”
Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising (2017, methodology): “The second dataset is provided in [19], which includes noisy images of 11 static scenes.”
Spatial-Adaptive Network for Single Image Denoising (2020, methodology): “In the comparisons of real noisy images, we choose DND [24], SIDD [1] and Nam [21] as our test datasets.”
Methods for image denoising using convolutional neural network: a review (2021, unknown): “…[125], EMNIST [126], COCO dataset [127], MIT-Adobe five k [128], ImageNet [129], BSD68 [130], Set 14 [131], Renoir [132], NC12 [133], NAM [134], SIDD [135], SUN397 [136], Set5 [137], CAVE [138],Harvard database [139], MRI brain dataset [140], LIVE1, Chelsea,DIV2K dataset [141], HIS…”
Image denoising using deep CNN with batch renormalization (2020, methodology): “Motivated by the fact, we choose cc [44] as the test dataset for real noisy image, as shown in Figure.”
Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset (2019, background): “Another approach to obtain a ground truth noise-free image is multi-frame fusion [46, 32, 1], which performs weighted averaging of a pre-aligned sequence of images taken from a static scene with a fixed camera setting.”
Unprocessing Images for Learned Raw Denoising (2018, methodology): “While [28] identifies limitations of traditional noise models, the work addresses more accurate models for denoising JPEG-compressed sRGB images, whereas we focus on denoising raw images.”
Deep Learning on Image Denoising: An overview (2019, methodology): “enes. The BSD68 contained 68 nature images. They were used to test the Gaussian denoiser and a denoiser of blind noise. The color-noisy image dataset included CBSD68, Kodak24 [57], McMaster [263], cc [160], DND [171], NC12 [112], SIDD [3] and Nam [160]. The Kodak24 and McMaster contained 24 and 18 c”
Benchmarking Denoising Algorithms with Real Photographs (2017, unknown): “Photographs with real noise are at best used for a qualitative analysis [25, 29], but often not at all.”
Attention-guided CNN for image denoising (2020, unknown): “BSD68 [41], Set12, CBSD68 [41], Kodak24 [12], McMaster [60] and cc [37], which consist of 68, 12, 68, 24, 18 and 15 images, respectively.”
A High-Quality Denoising Dataset for Smartphone Cameras (2018, methodology): “This strategy has been employed to generate noise-free images used in evaluating a denoising method [34], in evaluating a noise estimation method [5], in comparing algorithms for estimating noise level functions [21, 22], and for determining the parameters of a cross-channel noise model [24].”
Multi-stage image denoising with the wavelet transform (2022, methodology): “, BSD68 [14], Set12 [14], CBSD68 [14], Kodak24 [10] and CC [22].”
Learning to Restore Low-Light Images via Decomposition-and-Enhancement (2020, methodology): “Deep learning has also been widely applied to the denoising problem [33, 49, 50, 27, 37, 32].”
Real Image Denoising With Feature Attention (2019, methodology): “RNI15 [35], DND [46], Nam [42] and SSID [1].”