Modeling Multiscale Subbands of Photographic Images with Fields of Gaussian Scale Mixtures

By Siwei Lyu, Eero P. Simoncelli. 2009

89 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Probabilistic & Bayesian Methods

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

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Alan L. Yuille
5. Lei Zhang
6. Andrea Vedaldi
7. Andrew Zisserman
8. Trevor Darrell

In Media Technology

1. Lei Zhang
2. Eero P. Simoncelli
3. A. Buades
4. Guillermo Sapiro
5. Marc Lebrun
6. Jean-Michel Morel
7. Johannes Ballé
8. Pierre Vandergheynst

In Probabilistic & Bayesian Methods

1. Siwei Lyu
2. Eero P. Simoncelli
3. George Papandreou
4. Alan L. Yuille
5. Johannes Ballé
6. Pierre Vandergheynst
7. Guillermo Sapiro
8. Stéphane Mallat

Citations in the corpus

• A Nonlocal Bayesian Image Denoising Algorithm (2013, background): “It has received a more recent extension, reaching state-of-the-art performance, in [29].”
• Variational image compression with a scale hyperprior (2018, background): “Lyu and Simoncelli (2009) extend this model from spatially localized groups of wavelet coefficients to a global image model.”
• Gaussian sampling by local perturbations (2010, background): “The heavy tailed histograms of natural image filter responses are often conveniently approximated by kurtotic continuous parametric distributions [10,19,35].”
• Solving Inverse Problems With Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity (2010, background): “have shown impressive image denoi si g results by assuming Gaussian scale mixture models (deviati ng from GMM by assuming different scale factors in the mixture of Gaussians) on wavelet representations [36], [49], [65], and have recently extended its applications on image deblurrin g [35].”
• Image denoising with nonlocal spectral graph wavelets (2010, background): “We note that many authors have constructed statistical image models employing spatially varying statistical parameters, including [31, 37, 38].”
• Nonlinear Extraction of Independent Components of Natural Images Using Radial Gaussianization (2009, methodology): “Finally, we note that similar statistical behaviors have been observed in sound signals (Schwartz & Simoncelli, 2001; Turner & Sahani, 2008), and our preliminary investigation indicates that RG is also effective in removing dependencies in those signals (Lyu & Simoncelli, 2009).”