Noise2Flow: single-image conditional mean denoising flows from weak-anchor couplings
PurposeSingle-image denoising is needed when clean targets and repeated acquisitions are unavailable, as in low-dose computed tomography (CT) and fluorescence microscopy. Existing per-image methods often assume pixel-wise noise independence, which fails under spatially correlated noise, and imperfect single-image denoisers commonly leave residual noise. We learn a proxy mean-velocity direction field from one noisy image so that a single transport step exceeds the imperfect anchors used as supervision.ApproachNoise2Flow runs weak single-image denoisers on the noisy image to form source–target couplings. The displacement from input to anchor is a directional proxy for the mean restoration velocity. For each imposed linear segment, MeanFlow’s finite-interval average velocity reduces exactly to a constant secant. A flow network is trained with a direction-normalized objective that regularizes predictions at states in a stochastic tube around the noisy-to-anchor segment toward a common secant direction. At inference, the weak denoisers are discarded; one update with a calibrated transport budget restores the image.ResultsOn the fluorescence microscopy denoising (FMD) test set of 48 images, Noise2Flow reaches 34.91 dB peak signal-to-noise ratio and 0.887 structural similarity, 0.52 dB above Filter2Noise, and 1.00 dB above Noise2Detail. On 1311 low-dose CT slices from 10 Mayo Clinic patients, it reaches 28.82 dB and 0.714, 0.91 dB above Filter2Noise and 1.23 dB above Noise2Detail. One-step inference is within 0.11 dB of 10-step Heun; tube sampling improves the 10-step Heun result relative to on-segment training; a calibrated extrapolation factor moves the flow past residual-noise anchors of varying quality.ConclusionsA proxy mean-velocity direction field can be learned from a single noisy medical image by treating weak-denoiser outputs as directional anchors rather than final targets. The straight proxy path defines the one-step endpoint update; tube regularization and calibrated extrapolation carry that update past residual-noise anchors. The learned flow exceeds residual-noise anchors and supports reference-free restoration in data-limited imaging.
Authors
- Linda-Sophie Schneider (ORCID: https://orcid.org/0009-0002-6195-9859)
- Mingxuan Gu (ORCID: https://orcid.org/0000-0002-5244-4397)
- Zijin Yang (ORCID: https://orcid.org/0009-0008-8899-2249)
- Siming Bayer (ORCID: https://orcid.org/0000-0003-2874-4805)
- Daiqi Liu (ORCID: https://orcid.org/0009-0001-0905-3833)
- Linghan Cai (ORCID: https://orcid.org/0000-0002-7931-7697)
- Andreas Maier (ORCID: https://orcid.org/0000-0002-9550-5284)
- Ge Hu (ORCID: https://orcid.org/0000-0003-0808-9575)
- Siyuan Mei (ORCID: https://orcid.org/0009-0002-1136-2501)
- Y. J. Sun (ORCID: https://orcid.org/0000-0002-0249-5989)
- Chengze Ye (ORCID: https://orcid.org/0009-0001-0221-506X)
- Lan Song
- Fei Wu
Institutions
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Harbin Institute of Technology (CN)
- Peking Union Medical College Hospital (CN)
Publication Details
- Journal
- Journal of medical imaging
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1117/1.jmi.13.6.064002
- Primary Topic
- Image and Signal Denoising Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00