Content-aware Masked Image Modeling Transformer for Stereo Image Compression

arXiv:2403.08505v1 Announce Type: cross
Abstract: Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disparity characteristics inherent in stereo images, which leads to suboptimal rate-distortion results. In this paper, we propose a stereo image compression framework, named CAMSIC. CAMSIC independently transforms each image to latent representation and employs a powerful decoder-free Transformer entropy model to capture both spatial and …

abstract arxiv codec compression cs.ai cs.cv cs.mm eess.iv encode entropy however image images leads modeling paper rate results simple spatial struggle transformation transformer type