Preprint
Aug 2026
Local Epistemic Uncertainty Guided Active Sampling for Plug-and-play Diffusive Image Restoration
This work proposes a Local Epistemic Uncertainty Guided Active Sampling framework (LEADer), which improves the performance of multiple state-of-the-art DMIR methods, while significantly reducing sampling time with negligible memory overhead.
Jia-Qi Zhang, Zhengyang Pang, Rong-Rong Gao et al.
· 2 citations