arXiv Open Access 2023

Transformer-based Variable-rate Image Compression with Region-of-interest Control

Chia-Hao Kao Ying-Chieh Weng Yi-Hsin Chen Wei-Chen Chiu Wen-Hsiao Peng

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

eess.IV cs.CV

Penulis (5)

Chia-Hao Kao

Ying-Chieh Weng

Yi-Hsin Chen

Wei-Chen Chiu

Wen-Hsiao Peng

Format Sitasi

APA MLA BibTeX

Kao, C., Weng, Y., Chen, Y., Chiu, W., Peng, W. (2023). Transformer-based Variable-rate Image Compression with Region-of-interest Control. https://arxiv.org/abs/2305.10807

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓