Research map / Image generation / Image restoration
Fully Convolutional Pixel Adaptive Image Denoiser
Sungmin Cha, Taesup Moon
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 the a1 and a2 polynomial coefficients (use Z_i) (ablation) | FC-AIDE S+FT, a0 only · Image13 (BSD68, Gaussian) | PSNR (dB): 20.46 -> 29.33 | Improved |
| add the a1 and a2 polynomial coefficients (use Z_i) (ablation) | FC-AIDE S+FT, a0 only · BSD68 average (Gaussian) | PSNR (dB): 19.20 -> 29.31 | Improved |
| add a1 and a2 terms to the fine-tuned model (ablation) | FC-AIDE S (a1=a2=0) + FT · Image13 (BSD68, Gaussian) | PSNR (dB): 27.69 -> 29.33 | Improved |
| add a1 and a2 terms to the fine-tuned model (ablation) | FC-AIDE S (a1=a2=0) + FT · BSD68 average (Gaussian) | PSNR (dB): 27.68 -> 29.31 | Improved |
| add adaptive fine-tuning with the unbiased risk estimate (ablation) | FC-AIDE S (a1=a2=0) · Image13 (BSD68, Gaussian) | PSNR (dB): 26.99 -> 27.69 | Improved |
| add adaptive fine-tuning with the unbiased risk estimate (ablation) | FC-AIDE S (a1=a2=0) · BSD68 average (Gaussian) | PSNR (dB): 27.66 -> 27.68 | No clear effect |
Closest papers by meaning
- Adaptive Rates for Total Variation Image Denoising (JMLR 2020 · similarity 0.86)
- Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising (CVPR 2026 · similarity 0.86)
- Pixel2Pixel: A Pixelwise Approach for Zero-Shot Single Image Denoising (TPAMI 2025 · similarity 0.85)
- Robust Test-Time Adaptation for Single Image Denoising Using Deep Gaussian Prior (ICCV 2025 · similarity 0.85)
- Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural Networks (ICLR 2020 · similarity 0.85)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.83)
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.
