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)→
More from Research
- Slow models are a disaster in robotics: researcher dives into fixing latency for large VLAs — kvablack · 2026-11-16
- ICL alone may enable substantial continual learning, plot shows agents improve by Month 3 — xennygrimmato_ · 2026-11-16
- 1% erbium doping wrecks reactive ion etching of TeO₂ waveguides — jwt0625 · 2026-11-16
- Noise2Flow: trust the denoiser's direction, then walk 15% past its output — maier_ak · 2026-11-16
- VLM memory survey from 8 institutions: 4D taxonomy covering 300+ papers and ~70 benchmarks — 机器之心 · 2026-11-16
- miHoYo unveils Gamer, a VLA foundation model for real-time game agents — Run Luo · 2026-11-16