Research map / Image generation / Image restoration
Self-Supervised Image Denoising Using Implicit Deep Denoiser Prior
Read the paperCheck 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 IDDP instead of supervised U-Net | Image denoising · BSD300, Gaussian σ = 25 | PSNR (dB): 31.81 -> 31.70 | Hurt |
| Use IDDP instead of supervised U-Net | Image denoising · BSD300, Gaussian σ = 25 | SSIM: 0.897 -> 0.897 | No clear effect |
| Use IDDP instead of supervised U-Net | Image denoising · BSD300, Gaussian σ ∈ (0, 50] | PSNR (dB): 33.44 -> 33.32 | Hurt |
| Use IDDP instead of supervised U-Net | Image denoising · BSD300, Speckle v = 0.1 | PSNR (dB): 31.49 -> 30.96 | Hurt |
| Use IDDP instead of supervised U-Net | Image denoising · BSD300, Poisson λ = 30 | PSNR (dB): 31.09 -> 30.91 | Hurt |
| Add stop-gradient to the regularization target (ablation) | IDDP · Gaussian denoising | Image detail preservation | Helped |
| Remove stop-gradient from the regularization target (ablation) | IDDP · Gaussian denoising | Training stability | Hurt |
Closest papers by meaning
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.92)
- High-Quality Self-Supervised Deep Image Denoising (NeurIPS 2019 · similarity 0.91)
- IDR: Self-Supervised Image Denoising via Iterative Data Refinement (CVPR 2022 · similarity 0.91)
- Convexity-Aware Noise Calibration: A Self-Supervised Framework for Noise-Level-Unknown Image Denoising (CVPR 2026 · similarity 0.90)
- Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural Networks (ICLR 2020 · similarity 0.90)
- Deconstructing Denoising Diffusion Models for Self-Supervised Learning (ICLR 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.