Transformer-based Image Compression with Variable Image Quality Objectives

TL;DR

This paper introduces a Transformer-based image compression system that enables users to select different image quality objectives using prompt tokens, maintaining competitive rate-distortion performance while offering flexible quality trade-offs.

Contribution

The paper proposes a novel prompt-tuning approach with adaptive prompt tokens for variable quality image compression using a shared Transformer autoencoder.

Findings

Effective adaptation to different quality objectives demonstrated

Comparable rate-distortion performance to single-objective methods

Flexible quality trade-offs achieved with prompt tokens

Abstract

This paper presents a Transformer-based image compression system that allows for a variable image quality objective according to the user's preference. Optimizing a learned codec for different quality objectives leads to reconstructed images with varying visual characteristics. Our method provides the user with the flexibility to choose a trade-off between two image quality objectives using a single, shared model. Motivated by the success of prompt-tuning techniques, we introduce prompt tokens to condition our Transformer-based autoencoder. These prompt tokens are generated adaptively based on the user's preference and input image through learning a prompt generation network. Extensive experiments on commonly used quality metrics demonstrate the effectiveness of our method in adapting the encoding and/or decoding processes to a variable quality objective. While offering the additional flexibility, our proposed method performs comparably to the single-objective methods in terms of rate-distortion performance.