Rate distortion perception framework guides better image and video coding

An Overview of Rate-Distortion-Perception Theory

Information Theory

Summary

When pictures and videos are compressed, it's important to keep them looking good while using less space. This paper explains a way to balance file size, quality, and how natural images look using mathematical ideas. The authors review tools for measuring and improving this balance and suggest how to design better compression systems. This helps make videos and images smaller without making them look worse to people.

What this means in practice

  • For video codec engineers: Implement compression systems that optimize file size, image quality, and perception using the rate-distortion-perception framework.
  • For image compression developers: Design new image compressors guided by operational principles derived from the reviewed theory to improve visual results at low bitrates.

A survey. It maps existing work.

Authors

Jun Chen, Ashish Khisti

Abstract

This paper provides a comprehensive overview of the rate-distortion-perception framework, tracing its evolution from mathematical theory to practical deployment. We review the mathematical definition of the the mathematical definition of the Blau--Michaeli function and the associated coding theorems, examine computational methods for its evaluation, and discuss alternative formulations of the framework. Operational principles and design guidelines for modern image and video coding are also presented, highlighting the rate-distortion-perception framework as a rigorous foundation for developing next-generation perceptual compression systems.