Research map / Image generation / Image restoration
Real Image Denoising With Feature Attention
Saeed Anwar, Nick Barnes
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 long skip connection (LSC) (ablation) | plain RIDNet · BSD68 gray (ablation, 2e5 iterations) | PSNR (dB): 28.45 -> 28.77 | Improved |
| add short skip connection (SSC) (ablation) | plain RIDNet · BSD68 gray (ablation, 2e5 iterations) | PSNR (dB): 28.45 -> 28.81 | Improved |
| add feature attention (FA) (ablation) | plain RIDNet · BSD68 gray (ablation, 2e5 iterations) | PSNR (dB): 28.45 -> 28.52 | Improved |
| add FA to LSC + SSC (ablation) | RIDNet · BSD68 gray (ablation, 2e5 iterations) | PSNR (dB): 28.86 -> 28.90 | Improved |
| add long connection (LC) to LSC + SSC + FA (ablation) | RIDNet · BSD68 gray (ablation, 2e5 iterations) | PSNR (dB): 28.90 -> 28.96 | Improved |
| add LSC to SSC + LC + FA (ablation) | RIDNet · BSD68 gray (ablation, 2e5 iterations) | PSNR (dB): 28.86 -> 28.96 | Improved |
| add SSC to LSC (ablation) | RIDNet · BSD68 gray (ablation, 2e5 iterations) | PSNR (dB): 28.77 -> 28.86 | Improved |
| use RIDNet instead of CBDNet (single-stage, l1 loss only) | RIDNet · DND sRGB | PSNR (dB): 38.06 -> 39.23 | Improved |
| use RIDNet instead of CBDNet | RIDNet · SSID | PSNR (dB): 30.78 -> 38.71 | Improved |
| use RIDNet instead of CBDNet | RIDNet · Nam | PSNR (dB): 39.01 -> 39.09 | Improved |
| use RIDNet instead of FFDNet | RIDNet · BSD68 gray, sigma=50 | PSNR (dB): 26.29 -> 26.40 | Improved |
| use RIDNet instead of FFDNet | RIDNet · BSD68 color, sigma=50 | PSNR (dB): 27.96 -> 28.14 | Improved |
Closest papers by meaning
- Toward Convolutional Blind Denoising of Real Photographs (CVPR 2019 · similarity 0.92)
- Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural Networks (ICLR 2020 · similarity 0.91)
- Spatial-Adaptive Network for Single Image Denoising (ECCV 2020 · similarity 0.90)
- Unpaired Learning of Deep Image Denoising (ECCV 2020 · similarity 0.90)
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.89)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 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.
