A high accuracy and low complexity quality control method for image compression

TL;DR

This paper introduces a novel, accurate, and low-complexity quality control method for image compression that adapts QP to meet quality targets efficiently, suitable for large-scale image coding tasks.

Contribution

It proposes a concise {bb} domain linear distortion model and a data-driven parameter estimation method, decoupled from RDO, applicable across different image encoders.

Findings

Achieves highest control accuracy in the literature.

Lowest delay in quality control algorithms.

Reduces overall bitrate and bad case ratio in real-world applications.

Abstract

For large-scale still image coding tasks, the processing platform needs to ensure that the coded images meet the quality requirement. Therefore, the quality control algorithms that generate adaptive QP towards a target quality level for image coding are of significant research value. However, the existing quality control methods are limited by low accuracy, excessive computational cost, or temporal information dependence. In this paper, we propose a concise {\lambda} domain linear distortion model and an accurate model parameters estimation method based on the original data. Since the model parameters are obtained from the original data, the proposed method is decoupled from the RDO process and can be applied to different image encoders. Experiments show that the proposed quality control algorithm achieves the highest control accuracy and the lowest delay in the literature at the same time. The application of Alibaba's e-commerce platform also shows that the proposed algorithm can significantly reduce the overall bitrate while greatly reducing the bad case ratio.