Transformer-based Image Compression with Variable Image Quality Objectives

Chia Hao Kao, Yi Hsin Chen, Cheng Chien, Wei Chen Chiu, Wen Hsiao Peng

研究成果: Conference contribution同行評審

3 引文 斯高帕斯(Scopus)

摘要

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.

原文English
主出版物標題2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1718-1725
頁數8
ISBN(電子)9798350300673
DOIs
出版狀態Published - 2023
事件2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 - Taipei, 台灣
持續時間: 31 10月 20233 11月 2023

出版系列

名字2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Conference

Conference2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
國家/地區台灣
城市Taipei
期間31/10/233/11/23

指紋

深入研究「Transformer-based Image Compression with Variable Image Quality Objectives」主題。共同形成了獨特的指紋。

引用此