AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

C2N: Practical Generative Noise Modeling for Real-World Denoising

Geonwoon Jang, Wooseok Lee, Sanghyun Son, Kyoung Mu Lee

ICCV 2021 · Image generation › Fast diffusion sampling · approach: Denoising diffusion probabilistic models · 110 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 signal-dependent 1x1 module to the signal-independent generator (ablation)C2N generator · CBSD68 Poisson noisePSNR (dB): 35.21 -> 35.80Improved
add 3x3 convolution modules to the 1x1 generator (ablation)C2N generator · CBSD68 spatially correlated GaussianPSNR (dB): 28.91 -> 31.03Improved
add signal-dependent 1x1 module to the signal-independent generator (ablation)C2N generator · CBSD68 spatially correlated GaussianPSNR (dB): 26.09 -> 28.91Improved
add signal-dependent 1x1 module (ablation)C2N generator · CBSD68 Gaussian sigma=25PSNR (dB): 30.69 -> 30.66No clear effect
add 3x3 convolution modules to the 1x1 generator (ablation)C2N generator · CBSD68 Gaussian sigma=25PSNR (dB): 30.66 -> 30.40Hurt
add 3x3 convolution modules to the 1x1 generator (ablation)C2N generator · CBSD68 Poisson noisePSNR (dB): 35.80 -> 35.23Hurt
reduce clean samples for the noise generator from 36K to 360C2N · SIDD val (clean source S)PSNR (dB): 34.08 -> 31.84Hurt
reduce clean samples for the noise generator from 36K to 720C2N · SIDD val (clean source S)PSNR (dB): 34.08 -> 31.98Hurt
use DIV2K clean images instead of SIDD for denoiser trainingC2N · SIDD val (36K)PSNR (dB): 34.08 -> 31.72Hurt
use Urban100 clean images instead of SIDD for denoiser trainingC2N · SIDD val (36K)PSNR (dB): 34.08 -> 31.32Hurt
reduce clean samples from 720 to 360C2N · SIDD val (clean source S)PSNR (dB): 31.98 -> 31.84No clear effect

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