Research map / Image generation / Image restoration
Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior
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 |
|---|---|---|---|
| Train the pretrained denoiser using MC-SURE on undersampled-measurement-derived images (ablation) | LDAMP BM3D · i.i.d. Gaussian, 25% | PSNR: 31.20 -> 31.46 | Helped |
| Train the pretrained denoiser using MC-SURE on undersampled-measurement-derived images (ablation) | LDAMP BM3D · CDP, 25% | PSNR: 31.65 -> 33.26 | Helped |
| Train the pretrained denoiser using MC-SURE on undersampled-measurement-derived images (ablation) | LDAMP BM3D · CS-MRI, 60% | PSNR: 39.53 -> 40.62 | Helped |
| Include test-set measurements in denoiser pretraining and SURE training (ablation) | LDAMP SURE · i.i.d. Gaussian, 25% | PSNR: 31.46 -> 31.66 | Helped |
| Include test-set measurements in denoiser pretraining and SURE training (ablation) | LDAMP SURE · CDP, 25% | PSNR: 33.26 -> 33.51 | Helped |
| Include test-set measurements in denoiser pretraining and SURE training (ablation) | LDAMP SURE · CS-MRI, 60% | PSNR: 40.62 -> 40.71 | Helped |
| Use the proposed real-part noise estimator instead of the measurement-residual estimator (ablation) | LDAMP SURE · CDP | noise standard deviation estimation accuracy | Helped |
| Train the denoiser from undersampled measurements at extremely low sampling rates | LDAMP SURE · i.i.d. Gaussian, 5% | PSNR: 21.68 vs 21.88 | Hurt |
| Train the denoiser from undersampled measurements at extremely low sampling rates | LDAMP SURE · CDP, 5% | PSNR: 22.06 vs 22.57 | Hurt |
Closest papers by meaning
- Training Image Estimators without Image Ground Truth (NeurIPS 2019 · similarity 0.91)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.90)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.89)
- A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.88)
- Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing (CVPR 2025 · similarity 0.87)
- Stochastic Deep Restoration Priors for Imaging Inverse Problems (ICML 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.