Nonlinear image representation for efficient perceptual coding

By Jesus Malo, Irene Epifanio, Rafael Fonolla Navarro, Eero P. Simoncelli. 2006

123 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

End-to-end Optimized Image Compression (2016, neutral): “Some earlier results suggest that incorporating local normalization in linear block transform coding methods can improve coding performance (Malo et al., 2006), and can improve object recognition performance of cascaded convolutional neural networks (Jarrett et al., 2009).”
End-to-end optimization of nonlinear transform codes for perceptual quality (2016, methodology): “Further, previous methods required the decoder to invert the normalization transform, either by solving an iterative set of linear equations for every block [19], estimating the multipliers (i.”
Density Modeling of Images using a Generalized Normalization Transformation (2015, methodology): “Other types of iterations based on matrix inversion have been proposed for this purpose in the literature (Malo et al., 2006; Lyu & Simoncelli, 2008).”
Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes (2016, background): “, 2016), image compression (Malo et al., 2006), distributed neural representations (Simoncelli & Heeger, 1998), stimulus decoding (Ringach, 2009; Froudarakis et al.”
Iterative Gaussianization: From ICA to Random Rotations (2011, methodology): “Nonlinear methods using nonexplicit statistical models have been also proposed to this end in the denoising context [11], [12] and in the coding context [13], [14].”
Image Quality Assessment: Unifying Structure and Texture Similarity (2020, methodology): “Others have used transformations that mimic the early visual system [20], [37]–[39].”
Nonlinear image representation using divisive normalization (2008, methodology): “An obvious candidate is compression: a previous normalization representation based on a block-DCT decomposition exhibited substantial improvements in perceptual appearance of compressed images [15].”
Perceptual image quality assessment using a normalized Laplacian pyramid (2016, background): “We also show that the resulting quality metric provides a better account of human perceptual judgements than either MS-SSIM or a recently-published gain-control metric based on oriented filters.”
Eigen-Distortions of Hierarchical Representations (2017, unknown): “…and ubiquitous neural computations (local gain control, Carandini and Heeger [2012]) have a direct impact on perceptual sensitivity, a ﬁnding that is buttressed by several other published results (Malo et al. [2006], Lyu and Simoncelli [2008], Laparra et al. [2010, 2017], Ballé et al. [2017]).”
Perceptual Video Coding Based on SSIM-Inspired Divisive Normalization (2013, methodology): “In this work, we follow this framework, where previously coded frames are used to predict the current frame and only residuals after prediction are coded.”
Nonlinear Extraction of Independent Components of Natural Images Using Radial Gaussianization (2009, unknown): “Recently, several authors have developed invertible image transformations that incorporate DN (Malo et al, 2000 ; Malo, Epifanio, Navarro, & Simoncelli, 2006 ; Gluckman, 2006 ; Lyu & Simoncelli, 2007 ).”
A Deep Matrix Factorization Method for Learning Attribute Representations (2015, methodology): “[28], employing an adaptive non-linear image representation algorithm results in a reduction of the statistical and the perceptual redundancy amongst the representation elements.”