ScaleResfusion: זרימת ניגודיות רזידואלית על פי רשת וקטורית רזידואלית

תקציר מקורי באנגליתarXiv:2607.25275v2 Announce Type: replace-cross Abstract: Real-world Image Restoration (Real-IR) aims to recover high-quality (HQ) images from complex and unknown degradations. Recent diffusion-based methods have substantially improved perceptual quality, yet two obstacles remain: methods that sample from Gaussian noise require many steps and are often less faithful to the degraded input, whereas residual-based methods that start from the low-quality (LQ) image typically train task-specific models from scratch, with optimization objectives coupled to a particular noise scheduler, and therefore cannot reuse modern pre-trained generative priors. We present \textbf{ScaleResfusion}, which rewrites residual restoration as a scheduler-independent adaptation interface for pre-trained text-to-imag