Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising

By Jun Xu, Lei Zhang, Wangmeng Zuo, David Dapeng Zhang, Xiangchu Feng. IEEE International Conference on Computer Vision, 2015

385 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/b702a3c9c5c8a6f1df1ccf479dd70d1827ce9fe8

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

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (2016, methodology): “various models have been exploited for modeling image priors, including nonlocal self-similarity (NSS) models [1], [2], [3], [4], [5], sparse models [6], [7], [8], gradient models [9], [10], [11] and Markov random field (MRF) models [12], [13], [14].”
Non-Local Recurrent Network for Image Restoration (2018, methodology): “We do not list other methods [52, 3, 45, 6, 50] whose average performances are worse than DnCNN or MemNet.”
Real Image Denoising With Feature Attention (2019, background): “Many algorithms [67, 26, 59] investigated the maximum likelihood algorithm to learn a statistical prior, e.”
Deep Learning on Image Denoising: An overview (2019, methodology): “n 2020 use image denoising techniques to remove the noise and recover the latent observation from the given degraded image. Image denoising techniques have attracted much attention in recent 20 years [199, 201]. As the pioneer, sparse-based methods have been successfully applied in image denoising [”
MemNet: A Persistent Memory Network for Image Restoration (2017, methodology): “For qualitative comparisons, we use public codes of PCLR [2], PGPD [37] and WNNM [9].”
Methods for image denoising using convolutional neural network: a review (2021, methodology): “References [38, 39] were the first CNN architecture used in image denoising tasks.”
Unprocessing Images for Learned Raw Denoising (2018, methodology): “The move from simple, analytical techniques towards datadriven approaches continued in the form of dictionarylearning and basis-pursuit algorithms such as KSVD and Fields-of-Experts, which operate by finding image representations where sparsity holds or statistical regularities are well-modeled [2, ”
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections (2016, methodology): “BM3D [5], NCSR [8], EPLL [34], PCLR [3], PDPD [33] and WMMN [9] are compared with our method.”