AI RESEARCH
FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution
arXiv CS.CV
•
ArXi:2512.22647v2 Announce Type: replace Reinforcement Learning with Human Feedback (RLHF) has proven effective in image generation field guided by reward models to align human preferences. Motivated by this, adapting RLHF for Image Super-Resolution (ISR) tasks has shown promise in optimizing perceptual quality with Image Quality Assessment (IQA) model as reward models. However, the traditional IQA model usually output a single global score, which are exceptionally insensitive to local and fine-grained distortions.