CADC: Content Adaptive Diffusion-Based Generative Image Compression

ArXi:2602.21591v3 Announce Type: replace Diffusion-based generative image compression has nstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential lies in making the entire compression process content-adaptive, ensuring that the encoder's representation and the decoder's generative prior are dynamically aligned with the semantic and structural characteristics of the input image. However, existing methods suffer from three critical limitations that prevent effective content adaptation.