Semantic Image Compression for Rate, Distortion, and Performance Optimization: A Systematic Review with Quantitative Synthesis
The semantic image compression is revolutionizing the intelligent visual communication by compressing the image representation for machine perception and downstream tasks instead of human viewing. Although there have been great improvements with learned compression, semantic communication, and task-aware coding, there are still problems with architecture design, evaluation protocols, benchmark datasets, and deployment. This review, based on the PRISMA framework, examines 54 selected studies published from January 2018 to June 2026. Study-level coding was used to create a common coding scheme to perform a descriptive quantitative evidence synthesis, and frequencies and percentages calculated across learning architectures, optimization objectives, semantic preservation strategies, benchmark datasets, evaluation metrics, and application domains. The results demonstrate the straightforward shift from conventional rate–distortion optimization to semantic and task-aware compression. There are several major difficulties, including lack of standard evaluation frameworks, low cross-domain generalization, low reproducibility, and low unified metrics that combine compression efficiency and semantic fidelity. The review summarizes the existing methodologies, introduces new research trends, and offers useful insights for designing efficient semantic image compression systems for edge intelligence, medical imaging, autonomous platforms and communication networks empowered by artificial intelligence. The emphasis is on what steps can be taken towards learned image compression, which is a subject pursued by the Deep Learning (DL) community.