Papers › Noise Flow: Noise Modeling with Conditional Normalizing Flows
Noise Flow: Noise Modeling with Conditional Normalizing Flows
Abdelrahman Abdelhamed, Marcus A. Brubaker, Michael S. Brown
Modeling and synthesizing image noise is an important aspect in many computer vision applications. The long-standing additive white Gaussian and heteroscedastic (signal-dependent) noise models widely used in the literature provide only a coarse approximation of real sensor noise. This paper introduces Noise Flow, a powerful and accurate noise model based on recent normalizing flow architectures. Noise Flow combines well-established basic parametric noise models (e.g., signal-dependent noise) with the flexibility and expressiveness of normalizing flow networks. The result is a single, comprehensive, compact noise model containing fewer than 2500 parameters yet able to represent multiple cameras and gain factors. Noise Flow dramatically outperforms existing noise models, with 0.42 nats/pixel improvement over the camera-calibrated noise level functions, which translates to 52% improvement in the likelihood of sampled noise. Noise Flow represents the first serious attempt to go beyond simple parametric models to one that leverages the power of deep learning and data-driven noise distributions.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Denoising | ELD SonyA7S2 x100 | Noise Flow | PSNR (Raw) | 41.05 | #9 of 9 | Archive leaderboard | report |
| Image Denoising | ELD SonyA7S2 x100 | Noise Flow | SSIM (Raw) | 0.925 | #9 of 9 | Archive leaderboard | report |
| Image Denoising | ELD SonyA7S2 x200 | Noise Flow | PSNR (Raw) | 39.23 | #10 of 10 | Archive leaderboard | report |
| Image Denoising | ELD SonyA7S2 x200 | Noise Flow | SSIM (Raw) | 0.889 | #10 of 10 | Archive leaderboard | report |
| Image Denoising | SID SonyA7S2 x250 | Noise Flow | PSNR (Raw) | 35.80 | #10 of 10 | Archive leaderboard | report |
| Image Denoising | SID SonyA7S2 x250 | Noise Flow | SSIM (Raw) | 0.867 | #10 of 10 | Archive leaderboard | report |
| Image Denoising | SID x100 | Noise Flow | PSNR (Raw) | 38.89 | #8 of 8 | Archive leaderboard | report |
| Image Denoising | SID x100 | Noise Flow | SSIM | 0.929 | #8 of 8 | Archive leaderboard | report |
| Image Denoising | SID x300 | Noise Flow | PSNR (Raw) | 32.29 | #8 of 8 | Archive leaderboard | report |
| Image Denoising | SID x300 | Noise Flow | SSIM | 0.801 | #8 of 8 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections