Noise2Flow targets the hardest denoising case: one noisy image, no ground truth

maier_ak · x · 2026-11-16

Noise2Flow is led by Yipeng Sun at the Pattern Recognition Lab, with collaborators from Harbin Institute of Technology and Peking Union Medical College Hospital. The target scenario: in medical imaging, clean references often cannot exist—a clean CT would need a higher radiation dose, live cells move so the same frame can't be captured twice, and networks trained on one scanner generalize poorly. Noise2Flow denoises from a single noisy image alone.

Related event: Noise2Flow Denoises Single Noisy Medical Images Without Training Data(3 posts)→

Original post →

More from Research

Research channel →