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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add GSM and LCM together (ablation) | IDF · Mixture noise | PSNR: 27.07 -> 27.52 | Improved |
| add GSM only (ablation) | IDF · Spatial Gaussian | PSNR: 27.70 -> 27.44 | Hurt |
| add LCM only (ablation) | IDF · Mixture noise | PSNR: 27.07 -> 27.25 | Improved |
| add RMS normalization (ablation) | IDF · Mixture noise | PSNR: 27.13 -> 27.52 | Improved |
| add alternating dilation (ablation) | IDF · Spatial Gaussian | PSNR: 27.37 -> 27.78 | Improved |
| add power normalization (ablation) | IDF · Mixture noise | PSNR: 23.02 -> 27.52 | Improved |
| increase kernel size from 3 to 5 (ablation) | IDF · Mixture noise | PSNR: 27.52 -> 27.27 | Hurt |
| increase power factor from 1 to 3 (ablation) | IDF · Mixture noise | PSNR: 27.01 -> 27.52 | Improved |
| increase power factor from 3 to 4 (ablation) | IDF · Spatial Gaussian | PSNR: 27.78 -> 27.55 | Hurt |
| increase iterations T from 10 to 12 (ablation) | IDF · Mixture noise | PSNR: 27.52 -> 27.42 | Hurt |
| increase iterations T from 6 to 10 (ablation) | IDF · Mixture noise | PSNR: 27.32 -> 27.52 | Improved |
| raise DIC threshold kappa from 0.005 to 0.03 (ablation) | IDF with DIC · Spatial Gaussian average | PSNR: 28.28 -> 28.02; iterations 8.27 -> 5.93 | Mixed |
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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 1 of 1 shared result
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
- Adaptive Dynamic Filtering Network for Image Denoising (AAAI 2023 · similarity 0.93)
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.89)
- Fast and High Quality Image Denoising via Malleable Convolution (ECCV 2022 · similarity 0.89)
- IDR: Self-Supervised Image Denoising via Iterative Data Refinement (CVPR 2022 · similarity 0.89)
- Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural Networks (ICLR 2020 · similarity 0.89)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.87)
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.
