AI Paper Atlas

Research map / Image generation / Image restoration

IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising

Dongjin Kim, Jaekyun Ko, Muhammad Kashif Ali, Tae Hyun Kim

ICCV 2025 · Image generation › Image restoration · approach: Self-supervised image denoising · 7 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 GSM and LCM together (ablation)IDF · Mixture noisePSNR: 27.07 -> 27.52Improved
add GSM only (ablation)IDF · Spatial GaussianPSNR: 27.70 -> 27.44Hurt
add LCM only (ablation)IDF · Mixture noisePSNR: 27.07 -> 27.25Improved
add RMS normalization (ablation)IDF · Mixture noisePSNR: 27.13 -> 27.52Improved
add alternating dilation (ablation)IDF · Spatial GaussianPSNR: 27.37 -> 27.78Improved
add power normalization (ablation)IDF · Mixture noisePSNR: 23.02 -> 27.52Improved
increase kernel size from 3 to 5 (ablation)IDF · Mixture noisePSNR: 27.52 -> 27.27Hurt
increase power factor from 1 to 3 (ablation)IDF · Mixture noisePSNR: 27.01 -> 27.52Improved
increase power factor from 3 to 4 (ablation)IDF · Spatial GaussianPSNR: 27.78 -> 27.55Hurt
increase iterations T from 10 to 12 (ablation)IDF · Mixture noisePSNR: 27.52 -> 27.42Hurt
increase iterations T from 6 to 10 (ablation)IDF · Mixture noisePSNR: 27.32 -> 27.52Improved
raise DIC threshold kappa from 0.005 to 0.03 (ablation)IDF with DIC · Spatial Gaussian averagePSNR: 28.28 -> 28.02; iterations 8.27 -> 5.93Mixed

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