Color Image Denoising via Sparse 3D Collaborative Filtering with Grouping Constraint in Luminance-Chrominance Space

By Kostadin Dabov, Alessandro Foi, Vladimir Katkovnik, Karen O. Egiazarian. 2007 IEEE International Conference on Image Processing, 2007

510 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/ea9f1c9fc983d6f34d4c8fd1d03e7f7ad365030d

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

All-In-One Image Restoration for Unknown Corruption (2022, methodology): “Method CBM3D [5] DnCNN [53] IRCNN [54] FFDNet [55] BRDNet [40] DL [8] Ours”
Learning Multiscale Sparse Representations for Image and Video Restoration (2008, methodology): “THIS PAGE unclassified Standard Form 298 (Rev. 8-98) Prescribed by ANSI Std Z39-18 LEARNING MULTISCALE SPARSE REPRESENTATIONS FOR IMAGE AND VIDEO RESTORATION ∗ JULIEN MAIRAL† , GUILLERMO SAPIRO‡ , AND MICHAEL ELAD§ Abstract.”
SelfS2: Self-Supervised Transfer Learning for Sentinel-2 Multispectral Image Super-Resolution (2023, unknown): “In [35], a CBM3D [36] denoiser is plugged in, and this version”
Learning Deep CNN Denoiser Prior for Image Restoration (2017, methodology): “Perhaps the most successful color image prior modeling method is CBM3D [16].”
Recurrent Inference Machines for Solving Inverse Problems (2017, methodology): “ Denoising of 68 BSD-300 test images, ˙ = 25 after 8-bit quantization. Results for RTF-5 and CBM3D adopted from Schmidt et al. [20]. Results for full 100 test images in parenthesis. Method PSNR CBM3D [21] 30:18 RTF-5 [20] 30:57 RIM (ours) 30:84(30:67) After evaluating our model on 32 x 32 pixel imag”
Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising (2017, methodology): “We first compare MC-WNNM with the competing denoising methods [9, 11, 12, 14, 25, 28] on the 24 color images from the Kodak PhotoCD Dataset (http://r0k.”
Residual Dense Network for Image Restoration (2018, methodology): “BSD68: 163085 GT Noisy (σ=50) CBM3D [72] TNRD [21] RED [22]”
Image matting for fusion of multi-focus images in dynamic scenes (2013, methodology): “In order to remove these noises, a fast denoising method [36] is performed on Fig.”
A High-Quality Denoising Dataset for Smartphone Cameras (2018, methodology): “For BM3D [10], we applied AnscombeBM3D [23] in raw-RGB space and CBM3D [9] in sRGB space.”
Toward Convolutional Blind Denoising of Real Photographs (2018, methodology): “(a) Noisy (b) CDnCNN-B [4] (c) BM3D [8] (d) Ours”
WIRE: Wavelet Implicit Neural Representations (2023, methodology): “We denoised the original 512 × 512 image [5] with BM3D [14] ( σ = 0 .”
Residual Non-local Attention Networks for Image Restoration (2019, methodology): “It was lately introduced in BM3D (Dabov et al., 2007b) Attention mechanisms.”
Real Image Denoising With Feature Attention (2019, background): “Noise Methods Levels CBM3D [17] MLP [12] TNRD [15] DnCNN [59] IrCNN [60] CNLNet [36] FFDNet [61] Ours 15 33.”
Sparse Representation for Computer Vision and Pattern Recognition (2010, result): “State-of-the-art results obtained in [51] are “shared” with those in [ 19 ], which extends the non-local means approach developed in [5], [12].”
High-Quality Self-Supervised Deep Image Denoising (2019, methodology): “With both known and automatically estimated (using the method of Chen et al. [5]) noise parameters, CBM3D outperforms our ablated setups but remains far from the quality of our full method and the baseline methods.”
Spatial-Adaptive Network for Single Image Denoising (2020, methodology): “CBM3D results in pseudo artifacts.”
Video Denoising, Deblocking, and Enhancement Through Separable 4-D Nonlocal Spatiotemporal Transforms (2012, methodology): “Then, leveraging the approach presented in [10] and [21], we generalize V-BM4D to perform collaborative filtering of color (multi-channel) data.”