AI RESEARCH
SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression
arXiv CS.CV
•
ArXi:2605.04560v1 Announce Type: new Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or diffusion models, at the cost of substantial model complexity. To this end, we present an efficient perceptual image compression method that exploits the long-range modeling capability and linear computational complexity of state space models, with a particular focus on Mamba.