Zihao Fan

FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution

Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) in image generation, recent work has adapted reward-based learning to image super-resolution (ISR) by using Image Quality Assessment (IQA) models as rewards. However, existing IQA models typically output only a single globa