Research map / Image generation / Image restoration
Patch-Craft Self-Supervised Training for Correlated Image Denoising
Gregory Vaksman, Michael Elad
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 |
|---|---|---|---|
| Use Patch-Craft training instead of oracle BM3D | Image denoising on DAVIS correlated Gaussian noise · DAVIS correlated Gaussian average | PSNR: 33.27 -> 34.80 | Improved |
| Use Patch-Craft training instead of oracle BM3D | Image denoising on DAVIS correlated Gaussian noise · DAVIS correlated Gaussian average | SSIM: 0.875 -> 0.919 | Improved |
| Use Patch-Craft training instead of oracle BM3D | Image denoising on CRVD real-world noise · CRVD real-world noise average | PSNR: 36.47 -> 37.16 | Improved |
| Use Patch-Craft training instead of oracle BM3D | Image denoising on CRVD real-world noise · CRVD real-world noise average | SSIM: 0.951 -> 0.961 | Improved |
| Exclude training pairs whose input-residual covariance falls below a threshold (ablation) | Patch-Craft · Correlated Gaussian and real-world denoising | denoising performance | Improved |
Closest papers by meaning
- Iterative Denoiser and Noise Estimator for Self-Supervised Image Denoising (ICCV 2023 · similarity 0.90)
- High-Quality Self-Supervised Deep Image Denoising (NeurIPS 2019 · similarity 0.89)
- CVF-SID: Cyclic Multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise From Image (CVPR 2022 · similarity 0.89)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 2025 · similarity 0.89)
- Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising (CVPR 2025 · similarity 0.87)
- Zero-Shot Noise2Mean: Gap Minimization for Efficient Denoising from a Single Noisy Image (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.
