Region of Interest Scalable Image Compression Using Semantic Communications
Prabhath Samarathunga, Vishnu Sai Sankeerth Gowrisetty, Thanuj Fernando, Yasith Ganearachchi, Anil Fernando · 2024
Growing consumer demand for media content across a wide range of devices has made scalable image compression vital in the current media landscape. Image compression is conventionally achieved by means of statistical signal processing, but since recently deep learning techniques have been widely adopted as well. Capabilities of such systems also enable accurate identification of regions of interest in images, leading to optimized performance in most applications. This paper proposes a region-of-interest scalable image compression system using semantic communications, where an autoencoder-based semantic encoder performs the base-level compression, while a Semantic Mask Extracting Transformer (SeMExT) enables identification of regions of interest to create enhancement layers with different quality levels using a scalable JPEG encoder. When benchmarked against scalable JPEG across a variety of images, the proposed system demonstrates significantly improved compressive performance. The base layer achieved 61.4 times more compression on average, along with better rate-distortion performance at any given quality level.