AI Paper Atlas

Research map / Image generation / Image restoration

Iterative Denoiser and Noise Estimator for Self-Supervised Image Denoising

Yunhao Zou, Chenggang Yan, Ying Fu

ICCV 2023 · Image generation › Image restoration · approach: Self-supervised image denoising · 23 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 patch variance loss for the noise estimator (ablation)DCD-Net · Kodak, Gaussian sigma=25PSNR (dB): 24.21 -> 32.27Improved
decay patch variance loss weight to zero over training instead of keeping it constant (ablation)DCD-Net · Kodak, Gaussian sigma=25PSNR (dB): 31.86 -> 32.27Improved
use patch size 8 for patch variance loss instead of global or other sizes (ablation)DCD-Net · Kodak, Gaussian sigma=25PSNR (dB): 32.18 (global) -> 32.27Improved
add N2N loss ramped up over training (ablation)DCD-Net · Kodak, Gaussian sigma=25PSNR (dB): 31.81 -> 32.27Improved
include blind-spot network for initial coarse denoising (ablation)DCD-Net · Kodak, Gaussian sigma=25PSNR (dB): 14.46 -> 32.27Improved
anneal blind-spot loss weight to zero instead of keeping it constant (ablation)DCD-Net · Kodak, Gaussian sigma=25PSNR (dB): 31.75 -> 32.27Improved
DCD-Net versus B2U on Poisson noiseDCD-Net · Kodak, Poisson lambda=30PSNR (dB): 31.64 (B2U) vs 31.60 (ours)No clear effect
use DCD-Net instead of B2U for training costDCD-Net · SIDD raw-RGBrelative training cost: x17 -> x3Improved
R2R using known noise level prior on real noiseR2R · SIDD raw-RGBPSNR (dB): 51.40 (ours) vs 47.20 (R2R)Hurt

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