AI Paper Atlas

Research map / Image generation / Image restoration

Learning Camera-Aware Noise Models

Ke-Chi Chang, Ren Wang, Hung-Jin Lin, Yu-Lun Liu, Chia-Ping Chen, Yu-Lin Chang, Hwann-Tzong Chen

ECCV 2020 · Image generation › Image restoration · approach: Raw and low-light noise modeling · 52 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 feature matching loss (ablation)CA-NoiseGAN · SIDD noise modelingKL divergence: 0.01445 -> 0.01374Improved
add Camera-Encoding Network without triplet loss (ablation)CA-NoiseGAN · SIDD noise modelingKL divergence: 0.01374 -> 0.01412No clear effect
add triplet loss to the Camera-Encoding Network (ablation)CA-NoiseGAN · SIDD noise modelingKL divergence: 0.01412 -> 0.00159Improved
use Poisson-Gaussian instead of Gaussian as initial noise (ablation)CA-NoiseGAN · SIDD noise modelingKL divergence: 0.06265 -> 0.00159Improved
use CA-NoiseGAN instead of Noise FlowDnCNN denoiser · SIDD real-world denoising (500k)PSNR: 48.52 -> 48.71Improved
use CA-NoiseGAN instead of Noise Flownoise model · SIDD noise modelingKL divergence: 0.00912 -> 0.00159Improved
add real data to learned-noise-model synthetic trainingDnCNN denoiser · SIDD real-world denoising (500k)PSNR: 48.71 -> 48.72No clear effect
increase noise model training data from 100k to 500kCA-NoiseGAN · SIDD real-world denoisingPSNR: 47.97 -> 48.71Improved
add Camera-Encoding Network with triplet loss (ablation)camera-specific denoisers · SIDD camera IPPSNR: 57.4672 -> 58.6073Improved
add Camera-Encoding Network with triplet loss (ablation)camera-specific denoisers · SIDD camera N6PSNR: 44.7954 -> 46.4726Improved
add Camera-Encoding Network without triplet loss (ablation)camera-specific denoisers · SIDD cameras (IP, GP, S6, N6, G4)PSNR: 57.4672 -> 49.8788 (IP); 44.7954 -> 41.8447 (N6)Mixed
use latent vector from a different cameraCA-NoiseGAN · SIDD noise modelingKL divergence: 0.00159 -> 0.01324Hurt

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