AI RESEARCH

Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression

arXiv CS.CV

ArXi:2604.10546v1 Announce Type: new The rapid growth of visual data under stringent storage and bandwidth constraints makes extremely low-bitrate image compression increasingly important. While Vector Quantization (VQ) offers strong structural fidelity, existing methods lack a principled mechanism for joint rate-distortion (RD) optimization due to the disconnect between representation learning and entropy modeling.