Noise2Fast: A Fast Self-Supervised Single Image Blind Denoiser
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Image noise is a common problem in light microscopy. This is particularly true in real-time live-cell imaging applications where long-term cell viability necessitates low-light conditions. Modern denoisers are typically trained on a representative dataset, sometimes consisting of just unpaired noisy shots. However when data is acquired in real time to track dynamic cellular processes, it isn't always practical nor economical to generate these training sets. Recent approaches allow us to denoise single images without a training set. But all such methods to date are too slow to be integrated into imaging pipelines that require rapid, real-time analysis. To overcome these limitations we present Noise2Fast. Noise2Fast uses a novel downsampling tehcnique we refer to as "checkerboard downsampling", combined with convergence criteria that enable it to achieve an average 200 fold speed increase over the best comparable method, with only a 0.67 drop in PSNR making it the second most accurate blind single image denoiser we tested. We integrate Noise2Fast into real-time multi-modal imaging applications and demonstrate its broad applicability to diverse imaging and analysis pipelines.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.126 | 0.033 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it