AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Noise Flow: Noise Modeling With Conditional Normalizing Flows

Abdelrahman Abdelhamed, Marcus A. Brubaker, Michael S. Brown

ICCV 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Normalizing flow training and design · 194 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add camera-specific gain parameters to the signal-dependent and gain layers (ablation)Noise Flow (S-G) · SIDD noise modelingNLL: -3.431 -> -3.511Improved
add camera-specific gain parameters (ablation)Noise Flow (S-G) · SIDD noise synthesismarginal KL divergence: 0.067 -> 0.010Improved
add one unconditional flow step (affine coupling + 1x1 conv) around each layer (ablation)Noise Flow (S-G-CAM) · SIDD noise modelingNLL: -3.511 -> -3.518Improved
increase unconditional flow steps from one to four (ablation)Noise Flow · SIDD noise modelingNLL: -3.518 -> -3.521Improved
increase unconditional flow steps from one to four (ablation)Noise Flow · SIDD noise synthesismarginal KL divergence: 0.009 -> 0.008Improved
replace Gaussian model with Noise Flownoise density model · SIDD noise modelingNLL: -2.831 -> -3.521Improved
replace camera NLF with Noise Flownoise density model · SIDD noise modelingNLL: -3.105 -> -3.521Improved
replace camera NLF with Noise Flow for noise synthesisnoise synthesis · SIDD noise synthesismarginal KL divergence: 0.052 -> 0.008Improved
train DnCNN on Noise Flow noise instead of Gaussian noiseDnCNN · SIDD-Validation denoisingPSNR: 43.63 -> 48.52Improved
train DnCNN on Noise Flow noise instead of camera NLF noiseDnCNN · SIDD-Validation denoisingPSNR: 44.99 -> 48.52Improved
train DnCNN on Noise Flow synthetic noise instead of real noisy/clean pairsDnCNN · SIDD-Validation denoisingPSNR: 47.08 -> 48.52Improved
train DnCNN on Noise Flow noise instead of real noiseDnCNN · SIDD-Validation denoisingSSIM: 0.989 -> 0.992Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy