Research map / Image generation / Image restoration
Recorrupted-to-Recorrupted: Unsupervised Deep 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 prediction scheme (16) rather than direct Fθ*(y) prediction (ablation) | R2R · BSD68, σ = 25 and σ = 50 | PSNR (dB): 28.89 -> 29.14; 25.86 -> 26.12 | Helped |
| Vary the recorruption factor α from 0.1 to 1 (ablation) | R2R · BSD68, σ = 25 and σ = 50 | PSNR (dB): α = 1, 0.5, 0.3, 0.1: 28.81, 29.14, 29.03, 28.98; 25.81, 26.12, 25.93, 25.74 | No clear effect |
| Allow 10% noise-level estimation error (ablation) | R2R · BSD68, σ = 25 and σ = 50 | PSNR (dB): 29.09 vs 29.14; 26.07 vs 26.12 | No clear effect |
Closest papers by meaning
- Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise (CVPR 2025 · similarity 0.89)
- Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Clean Images (NeurIPS 2021 · similarity 0.88)
- An Unsupervised Deep Learning Approach for Real-World Image Denoising (ICLR 2021 · similarity 0.87)
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.87)
- High-Quality Self-Supervised Deep Image Denoising (NeurIPS 2019 · similarity 0.87)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 2025 · similarity 0.86)
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.