Research map / Image generation / Image restoration
Deep Convolutional Dictionary Learning for Image Denoising
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 DCDicL rather than the strongest listed baseline | grayscale denoising · Set12, BSD68, and Urban100 at σ=15, 25, and 50 | PSNR | Helped |
| use DCDicL rather than the strongest listed baseline | color denoising · CBSD68, Kodak24, McMaster, and Urban100 at σ=15, 25, and 50 | PSNR | Helped |
| replace a universal dictionary with an image-adaptive dictionary (ablation) | DCDicL · CBSD68, Kodak24, McMaster, and Urban100, σ=15, 25, and 50 | PSNR: 34.23 -> 34.35; 31.63 -> 31.74; 28.45 -> 28.57; 35.20 -> 35.35; 32.80 -> 32.95; 29.78 -> 29.95; 35.24 -> 35.46; 33.01 -> | Helped |
| increase dictionary atom spatial size k among 3, 5, and 7 (ablation) | DCDicL · Set12, σ=25 | PSNR | Helped |
| increase the number of stages T and residual units nr (ablation) | DCDicL · Set12, σ=25 | PSNR | Helped |
Closest papers by meaning
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.87)
- Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders (ICLR 2021 · similarity 0.87)
- Convolutional dictionary learning based auto-encoders for natural exponential-family distributions (ICML 2020 · similarity 0.87)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.85)
- DenoiseRep: Denoising Model for Representation Learning (NeurIPS 2024 · similarity 0.84)
- Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks (CVPR 2025 · similarity 0.84)
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.