Research map / Image generation / Image restoration
Joint Demosaicing and Denoising With Self Guidance
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 SGNet instead of Deepjoint | Joint demosaicing and denoising · Dense texture, σ=10 | PSNR: 43.26 -> 44.23 | Helped |
| Use SGNet instead of Kokkinos | Joint demosaicing and denoising · MIT moire, σ=10 | PSNR: 30.01 -> 30.09 | Helped |
| Use SGNet instead of Kokkinos | Joint demosaicing and denoising · Urban100, σ=10 | PSNR: 31.73 -> 32.14 | Helped |
| Use SGNet instead of TENet | Joint demosaicing, denoising and super-resolution · Dense texture, σ=10 | PSNR: 42.70 -> 43.81 | Helped |
| Use SGNet instead of TENet | Joint demosaicing, denoising and super-resolution · Sparse texture, σ=10 | PSNR: 43.86 -> 43.91 | Helped |
| Add edge-aware smoothness loss (ablation) | SGNet · Dense texture, σ=10 | PSNR: 44.01 -> 44.23 | Helped |
| Add adaptive-threshold edge loss (ablation) | SGNet · Dense texture, σ=10 | PSNR: 43.92 -> 44.23 | Helped |
| Add density-map guidance (ablation) | SGNet · Dense texture, σ=10 | PSNR: 43.86 -> 44.23 | Helped |
| Add green-channel reconstruction branch (ablation) | SGNet · Dense texture, σ=10 | PSNR: 42.90 -> 44.23 | Helped |
| Use spatially adaptive green guidance instead of concatenation guidance (ablation) | SGNet · Dense texture, σ=10 | PSNR: 43.31 -> 44.23 | Helped |
| Add edge-aware smoothness loss (ablation) | SGNet · Dense texture, σ=10 | LPIPS: 0.03574 -> 0.03280 | Helped |
| Add adaptive-threshold edge loss (ablation) | SGNet · Dense texture, σ=10 | LPIPS: 0.03752 -> 0.03280 | Helped |
Closest papers by meaning
- Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance (CVPR 2024 · similarity 0.87)
- Quad Bayer Joint Demosaicing and Denoising Based on Dual Encoder Network with Joint Residual Learning (AAAI 2024 · similarity 0.86)
- Zero-Shot Noise2Mean: Gap Minimization for Efficient Denoising from a Single Noisy Image (AAAI 2025 · similarity 0.85)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 2025 · similarity 0.85)
- Joint Demosaicing and Denoising for Spike Camera (AAAI 2024 · similarity 0.85)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 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.