AI Paper Atlas

Research map / Image generation / Image restoration

Physics-based Noise Modeling for Extreme Low-light Photography

Kaixuan Wei, Ying Fu, Yinqiang Zheng, Jiaolong Yang

TPAMI 2021 · Image generation › Image restoration · approach: Raw and low-light noise modeling · 141 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
replace Gaussian shot-noise approximation with true Poisson (ablation)G+P · SID Sony (x250)PSNR: 35.67 -> 37.27Improved
replace Gaussian read noise with Tukey lambda model (ablation)G+P* · SID Sony (x250)PSNR: 37.27 -> 38.20Improved
add color-wise bias noise B (ablation)G*+P* · SID Sony (x250)PSNR: 38.20 -> 40.44Improved
add row noise R (ablation)G*+P*+B · SID Sony (x250)PSNR: 40.44 -> 40.55Improved
add uniform quantization noise U (ablation)G*+P*+B+R · SID Sony (x250)PSNR: 40.55 -> 40.60Improved
add Gaussian-approx photon noise P to Gaussian read noise (ablation)G · SID Sony (x250)PSNR: 34.83 -> 35.67Improved
add color bias B (ablation)G*+P* · SID Sony (x300)PSNR: 34.56 -> 36.29Improved
train on synthetic noise instead of paired real datadenoiser U-Net · SID Sony (x250)PSNR: 40.59 -> 40.60No clear effect
train on synthetic noise instead of paired real datadenoiser U-Net · ELD CanonEOS70D (x200)PSNR: 37.32 -> 38.78Improved
train on synthetic noise instead of paired real datadenoiser U-Net · SID Fuji (x250)PSNR: 38.56 -> 38.33Hurt
use physics-based model instead of G+Pdenoiser U-Net · SID Fuji (x250)PSNR: 34.86 -> 38.33Improved
train multi-frame fastDVDnet on synthetic dynamic video (D) instead of static video (S) (ablation)fastDVDnet · synthetic dynamic videoPSNR: 28.47 -> 37.48Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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