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.
@article{arxiv.2305.10807,
title = {Transformer-based Variable-rate Image Compression with Region-of-interest Control},
author = {Chia-Hao Kao and Ying-Chieh Weng and Yi-Hsin Chen and Wei-Chen Chiu and Wen-Hsiao Peng},
journal= {arXiv preprint arXiv:2305.10807},
year = {2023}
}