AI Paper Atlas

Research map / Image generation / Image restoration

Towards General Low-Light Raw Noise Synthesis and Modeling

Feng Zhang, Bin Xu, Zhiqiang Li, Xinran Liu, Qingbo Lu, Changxin Gao, Nong Sang

ICCV 2023 · Image generation › Image restoration · approach: Raw and low-light noise modeling · 34 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
separate noise into physics-based signal-dependent and learned signal-independent parts (ablation)noise synthesis model · SID (x300)PSNR: 33.05 -> 36.03Improved
add pre-trained Denoise-Net for image domain alignment (ablation)noise synthesis model · SID (x300)PSNR: 35.66 -> 36.03Improved
replace vanilla transformer discriminator with Fourier transformer discriminator (ablation)noise synthesis model · SID (x300)PSNR: 33.22 -> 36.03Improved
replace vanilla transformer discriminator with Fourier transformer discriminator (ablation)noise synthesis model · SID (x100)SSIM: 0.931 -> 0.956Improved
generative learned noise model instead of ELD physics-based noise modeldenoiser training data · LRD (-1EV)PSNR: 38.31 -> 38.89Improved
synthetic noise model vs ELD on ELD x100denoiser training data · ELD (x100)PSNR: 45.06 -> 44.95Hurt
train on synthetic noise instead of real paired data at highest ratiodenoiser training data · SID (x300)PSNR: 36.55 -> 36.03Hurt
train on synthetic noise instead of real paired data on SID x100denoiser training data · SID (x100)PSNR: 41.39 -> 41.95Improved

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