Exploring the Limits of Semantic Image Compression at Micro-bits per Pixel

arXiv:2402.13536v1 Announce Type: new
Abstract: Traditional methods, such as JPEG, perform image compression by operating on structural information, such as pixel values or frequency content. These methods are effective to bitrates around one bit per pixel (bpp) and higher at standard image sizes. In contrast, text-based semantic compression directly stores concepts and their relationships using natural language, which has evolved with humans to efficiently represent these salient concepts. These methods can operate at extremely low bitrates by disregarding structural information …

abstract arxiv compression contrast cs.ai cs.cv image information micro per pixel semantic standard text type values