Research map / Image generation / Image restoration
Non-Local Color Image Denoising With Convolutional Neural Networks
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use non-local patch grouping and joint filtering in place of a local denoising model | NLNet · BSDS 68 images, grayscale, σ=15 | PSNR (dB): 31.42 -> 31.52 | Helped |
| Use non-local patch grouping and joint filtering in place of a local denoising model | NLNet · BSDS 68 images, grayscale, σ=25 | PSNR (dB): 28.92 -> 29.03 | Helped |
| Use non-local patch grouping and joint filtering in place of a local denoising model | NLNet · BSDS 68 images, grayscale, σ=50 | PSNR (dB): 25.96 -> 26.07; 26.02 -> 26.07 | Mixed |
| Use the color non-local network rather than CBM3D | CNLNet · BSDS 68 images, color, σ=15 | PSNR (dB): 33.50 -> 33.69 | Helped |
| Use the color non-local network rather than CBM3D | CNLNet · BSDS 68 images, color, σ=25 | PSNR (dB): 30.69 -> 30.96 | Helped |
| Use the color non-local network rather than CBM3D | CNLNet · BSDS 68 images, color, σ=50 | PSNR (dB): 27.37 -> 27.64 | Helped |
| Use 7×7 patches instead of 5×5 patches (ablation) | NLNet · BSDS 68 images, grayscale, σ=15 | PSNR (dB): 31.49 -> 31.52 | No clear effect |
| Use 7×7 patches instead of 5×5 patches (ablation) | NLNet · BSDS 68 images, grayscale, σ=25 | PSNR (dB): 28.98 -> 29.03 | No clear effect |
| Use 7×7 patches instead of 5×5 patches (ablation) | NLNet · BSDS 68 images, grayscale, σ=50 | PSNR (dB): 25.99 -> 26.07 | No clear effect |
Closest papers by meaning
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.93)
- The Neural Tangent Link Between CNN Denoisers and Non-Local Filters (CVPR 2021 · similarity 0.89)
- Non-Local Recurrent Network for Image Restoration (NeurIPS 2018 · similarity 0.89)
- Efficient Deep Image Denoising via Class Specific Convolution (AAAI 2021 · similarity 0.89)
- Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural Networks (ICLR 2020 · similarity 0.89)
- DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables (CVPR 2025 · similarity 0.88)
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.