RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution
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. In this work, we propose RefReward-SR, a low-resolution (LR) reference-aware reward model for preference-aligned SR. Instead of relying on GT supervision or...
| Authors | Yushuai Song, Weize Quan, Weining Wang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 25 March 2026 |
| Last updated at source | 25 March 2026 |
Connected in the knowledge graph
- casyssong/RefSR-18KDataset · cited by
Models and datasets referencing this paper
- casyssong/RefSR-18KDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.