@inproceedings{eceda9044e2847ab92f304ceeac0f03e,
title = "Transformer-Based Variable-Rate Image Compression with Region-of-Interest Control",
abstract = "This paper proposes a transformer-based learned image compression system. It is capable of achieving variable-rate compression with a single model while supporting the region-of-interest (ROI) functionality. Inspired by prompt tuning, we introduce prompt generation networks to condition the transformer-based autoencoder of compression. Our prompt generation networks generate content-adaptive tokens according to the input image, an ROI mask, and a rate parameter. The separation of the ROI mask and the rate parameter allows an intuitive way to achieve variable-rate and ROI coding simultaneously. Extensive experiments validate the effectiveness of our proposed method and confirm its superiority over the other competing methods.",
keywords = "prompt tuning, region-of-interest, Transformer-based image compression, variable-rate compression",
author = "Kao, {Chia Hao} and Weng, {Ying Chieh} and Chen, {Yi Hsin} and Chiu, {Wei Chen} and Peng, {Wen Hsiao}",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 30th IEEE International Conference on Image Processing, ICIP 2023 ; Conference date: 08-10-2023 Through 11-10-2023",
year = "2023",
doi = "10.1109/ICIP49359.2023.10222853",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "2960--2964",
booktitle = "2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings",
address = "United States",
}