Noise2Flow 核心思路:不完美去噪方向可信,再前进 15% 即可

maier_ak · x · 2026-11-16

The author explains Noise2Flow's core observation: an imperfect denoiser is often right about the direction but wrong about the distance—the step from a noisy image toward its output usually points the right way (verified against ground-truth clean images). The method learns that direction from a single noisy image, fits a step length, and walks roughly 15% past the imperfect result, requiring only one network pass at the end—no clean reference or training set needed.

所属事件:Noise2Flow 实测:显微与低剂量 CT 去噪效果超越现有方法(2 条相关)→

原文链接 →

「研究」频道最新

更多「研究」频道 AI 资讯 →