[Paper] Deep Learning-based RGBA Image Compression with Masked Window-based Attention

• Published in: ITE TRANSACTIONS ON MEDIA TECHNOLOGY AND APPLICATIONS Vol. 13; no. 2; pp. 200 - 210
• Main Authors: Inazu, Yoshiki, Kimata, Hideaki
• Format: Journal Article
• Language: English
• Published: The Institute of Image Information and Television Engineers 2025
• Subjects: alpha channel; deep learning; image compression; masked window-based attention; RGBA
• ISSN: 2186-7364; 2186-7364
• DOI: 10.3169/mta.13.200

RGBA image that includes an alpha channel for transparency is common in real-world applications. Traditional RGBA compression methods apply the same methods to both RGB and alpha channel, but potentially leading to suboptimal results due to their different characteristics. This paper proposes a deep neural network that introduces attention modules individually suitable for RGB signals and alpha channel. The proposed method consists of two networks, one for the RGB signal and one for the alpha channel, with an appropriate attention module applied in each. In particular, a new attention module that focuses on the unmasked regions of the alpha channel is applied. In the evaluation, the proposed method is compared with a simple deep neural network with input and output layers extended from three to four channels and classical RGBA image compression methods.