End-to-end optimization of nonlinear transform codes for perceptual quality
Abstract
We introduce a general framework for end-to-end optimization of the rate--distortion performance of nonlinear transform codes assuming scalar quantization. The framework can be used to optimize any differentiable pair of analysis and synthesis transforms in combination with any differentiable perceptual metric. As an example, we consider a code built from a linear transform followed by a form of multi-dimensional local gain control. Distortion is measured with a state-of-the-art perceptual metric. When optimized over a large database of images, this representation offers substantial improvements in bitrate and perceptual appearance over fixed (DCT) codes, and over linear transform codes optimized for mean squared error.
Cite
@article{arxiv.1607.05006,
title = {End-to-end optimization of nonlinear transform codes for perceptual quality},
author = {Johannes Ballé and Valero Laparra and Eero P. Simoncelli},
journal= {arXiv preprint arXiv:1607.05006},
year = {2020}
}
Comments
Accepted as a conference contribution to Picture Coding Symposium 2016