Details

Autor(en) / Beteiligte

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

Titel

Transformer-Based Variable-Rate Image Compression with Region-of-Interest Control

Ist Teil von

• 2023 IEEE International Conference on Image Processing (ICIP), 2023, p.2960-2964

Ort / Verlag

IEEE

Erscheinungsjahr

2023

Quelle

IEEE/IET Electronic Library (IEL)

Beschreibungen/Notizen

• 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.