Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision
By Shuhang Gu, Qi Xie, Deyu Meng, Wangmeng Zuo, Xiangchu Feng, Lei Zhang. International Journal of Computer Vision, 2016
783 citations recorded by the source corpus.
Subfields: Computational Mechanics, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/2a1591fbe443b256d222c4732ef37b9b44642608
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
- Wangmeng Zuo
- Lei Zhang
- David Dapeng Zhang
- Kai Zhang
- Xiangchu Feng
- David J. Brady
- Xin Yuan
- Yunjin Chen
In Computer Vision and Pattern Recognition
- Lei Zhang
- Wangmeng Zuo
- Kai Zhang
- Luc Van Gool
- Chen Change Loy
- Radu Timofte
- Ming-Hsuan Yang
- Ling Shao
Citations in the corpus
- Reweighted Infrared Patch-Tensor Model With Both Nonlocal and Local Priors for Single-Frame Small Target Detection (2017, methodology): “Inspired by it, many improved RPCA models have been proposed [39]–[42].”
- Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising (2017, methodology): “mization (WNNM) method [3, 21], which exploits the image NSS property via low rank regularization, has achieved excellent denoising performance on grayscale images, we propose to extend WNNM to real color image denoising.”
- Deep Identity-aware Transfer of Facial Attributes (2016, background): “Conventional sparse [1], low rank [13], FRAME [43] and non-local similarity [3] based models usually are limited in capturing highly complex and long-range dependence between pixels.”
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (2016, methodology): “First, those methods generally involve a complex optimization problem in the testing stage, making the denoising process timeconsuming [7], [16].”
- Rank Minimization for Snapshot Compressive Imaging (2018, methodology): “In the application of denoising, the larger the singular values, the less they should be shrunk [24], [25], i.”
- ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (2023, background): “Traditional image SR methods primarily focus on designing more rational image priors based on our subjective knowledge, such as non-local similarity [27], low-rankness [28], sparsity [29, 30], and so on.”