AI RESEARCH
RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution
arXiv CS.CV
•
ArXi:2603.24198v1 Announce Type: new Recent advances in generative super-resolution (SR) have greatly improved visual realism, yet existing evaluation and optimization frameworks remain misaligned with human perception. Full-Reference and No-Reference metrics often fail to reflect perceptual preference, either penalizing semantically plausible details due to pixel misalignment or favoring visually sharp but inconsistent artifacts. Moreover, most SR methods rely on ground-truth (GT)-dependent distribution matching, which does not necessarily correspond to human judgments.