AI Paper Atlas

Research map / Image generation / Image restoration

One-Pot Multi-frame Denoising

Lujia Jin, Qing Guo, Zhao Shi, Lei Zhu, Qian Chen, Qiushi Ren, Yanye Lu

IJCV 2023 · Image generation › Image restoration · approach: Self-supervised image denoising · 2 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 N2N pairwise supervision with OPD-AL mutual supervisionN2N · Synthetic Gaussian noisePSNR: 27.48 -> 28.36Improved
replace N2N with OPD-ALN2N · Synthetic Gaussian noiseSSIM: 0.787 -> 0.807Improved
replace N2N with OPD-ALN2N · Synthetic Gaussian noiseRMSE: 0.048 -> 0.039Improved
replace N2N with OPD-RCN2N · Synthetic Poisson noisePSNR: 27.28 -> 28.22Improved
replace N2N with OPD-RCN2N · OCT speckle noisePSNR: 28.07 -> 30.69Improved
use unsupervised OPD-RC instead of supervised N2CN2C · Synthetic Gaussian noisePSNR: 28.04 -> 28.15Improved
use supervised multi-frame BPN instead of unsupervised OPD-ALOPD-AL · Synthetic Gaussian noisePSNR: 28.36 -> 33.84Hurt
use kernel-prediction supervised BPN instead of OPD-RCOPD-RC · OCT speckle noisePSNR: 30.69 -> 29.00Hurt
use self-supervised N2S instead of OPD-RCOPD-RC · OCT speckle noisePSNR: 30.69 -> 22.23Hurt
use alienation loss (OPD-AL) instead of random coupling (OPD-RC) (ablation)OPD · Synthetic Gaussian noisePSNR: 28.15 -> 28.36Mixed
use alienation loss (OPD-AL) instead of random coupling (OPD-RC) (ablation)OPD · OCT speckle noisePSNR: 30.69 -> 30.40Hurt

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