Research map / Image generation / Image restoration
YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency
Hansen Feng, Lizhi Wang, Yiqi Huang, Tong Li, Lin Zhu, Hua Huang
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 EM-VST instead of GAT+IAT (ablation) | YOND · SIDD | PSNR: 49.27 -> 51.60 | Improved |
| add EM-VST instead of GAT+UIAT (ablation) | YOND · SIDD | PSNR: 50.94 -> 51.60 | Improved |
| use SNR-Net instead of UNet (ablation) | YOND · SIDD | PSNR: 50.66 -> 51.60 | Improved |
| add SNR-guided branch to SNR-Net (ablation) | YOND · SIDD | PSNR: 51.44 -> 51.60 | Improved |
| add SNR-guided branch to SNR-Net (ablation) | YOND · SIDD | SSIM: 0.9911 -> 0.9895 | Hurt |
| use CNE instead of Foi single-step (ablation) | YOND · SIDD | PSNR: 50.80 -> 51.60 | Improved |
| add fine stage CNE after CameraNLF (ablation) | YOND · SIDD | PSNR: 49.29 -> 51.42 | Improved |
| add fine stage CNE after Zou (ablation) | YOND · SIDD | PSNR: 46.83 -> 50.84 | Improved |
| add fine stage CNE after PGE (ablation) | YOND · SIDD | PSNR: 50.24 -> 51.59 | Improved |
| add fine stage after CNE coarse (ablation) | YOND · SIDD | PSNR: 50.95 -> 51.60 | Improved |
| use calibrated noise parameters instead of CNE estimates (ablation) | YOND · LRID | PSNR: 0.1dB improvement | Improved |
| use camera-specific calibration (ELD) instead of blind noise parameters | ELD · ELD NikonD850 ISO 800-3200 | PSNR: 49.18 -> 50.61 | Improved |
Closest papers by meaning
- Calibration-Free Raw Image Denoising via Fine-Grained Noise Estimation (TPAMI 2025 · similarity 0.91)
- IDR: Self-Supervised Image Denoising via Iterative Data Refinement (CVPR 2022 · similarity 0.91)
- Toward Convolutional Blind Denoising of Real Photographs (CVPR 2019 · similarity 0.91)
- Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising (CVPR 2026 · similarity 0.89)
- FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise (CVPR 2021 · similarity 0.89)
- Rethinking Noise Synthesis and Modeling in Raw Denoising (ICCV 2021 · similarity 0.89)
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.
