Adaptive Fused Prior Transfer for Controllable Generative Image Compression

ArXi:2605.16817v1 Announce Type: cross Learned image compression has achieved competitive rate-distortion performance, but very-low-bitrate reconstruction remains difficult because the transmitted representation often cannot preserve fine textures and local structures. Perceptual and generative codecs address this problem by using learned reconstruction priors, and controllable codecs allow one model to cover different bitrate and reconstruction preferences.