Work

End-to-end optimization of nonlinear transform codes for perceptual quality

Year: 2016

Type: conference-paper

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.

Source: Picture Coding Symposium

DOI: 10.1109/pcs.2016.7906310

Authors: Jona Ballé, Valero Laparra, Eero P. Simoncelli

Institutions: Courant Institute of Mathematical Sciences, New York University

Language: English

Topic: Advanced Data Compression Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Generalitat Valenciana

Award: G761697526