Image denoising using mixtures of Gaussian scale mixtures
By Jose A. Guerrero-Colon, Eero P. Simoncelli, Javier Portilla. 2008
44 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
- Luc Van Gool
- Ming-Hsuan Yang
- Lei Zhang
- Dacheng Tao
- Andrew Zisserman
- Andrea Vedaldi
- Trevor Darrell
- Xiaogang Wang
In Media Technology
- Karen O. Egiazarian
- Lei Zhang
- Alessandro Foi
- Vladimir Katkovnik
- Eero P. Simoncelli
- Kostadin Dabov
- Wangmeng Zuo
- Lucas Theis
Citations in the corpus
- Density Modeling of Images using a Generalized Normalization Transformation (2015, background): “, finite mixtures of Gaussians or GSMs (Guerrero-Colón et al., 2008; Lyu & Simoncelli, 2009a; Zoran & Weiss, 2012; Theis et al., 2012), and sparse factorization (Culpepper et al.”
- Mixtures of Conditional Gaussian Scale Mixtures Applied to Multiscale Image Representations (2011, positive): “In computer science, they are used as priors in applications such as image denoising [3], compression [4], or reconstruction [5], and to learn image representations that can be used in object recognition tasks [6].”
- BM3D Image Denoising with Shape-Adaptive Principal Component Analysis (2009, background): “Some of the most recent and successful advances are based on: Gaussian scale mixtures (GSM) modeling in overcomplete multiscale transform domain [9], [15], [8]; learned dictionaries of atoms to (cid:222) lter small square neighborhoods [6]; steering kernel regression [16] (also combined with…”
- Efficient Visual Pretraining with Contrastive Detection (2021, background): “Perceptual grouping [32, 41]—the idea that low and mid-level regularities in the data such as color, orientation and texture allow for approximately parsing a scene into connected surfaces or object parts—has long been theorized to be a powerful prior for vision [22, 40, 56].”
- How Sensitive Is the Human Visual System to the Local Statistics of Natural Images? (2013, methodology): “Roughly speaking, MEC is able to capture similar correlations like the Karklin & Lewicki model [11], or the mixture of Gaussian scale mixtures model [32], yet MEC uses hard clustering to partition the natural image distribution which we make use of in the stimulus generation process.”