IQA

Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward featured image

Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward

Difficulty-adaptive RL for diffusion restoration with IQA reward.

Wenjie Shu

• Nov 1, 2025 • 1 min read