Research map / Image generation / Image restoration
A Poisson-Gaussian Denoising Dataset With Real Fluorescence Microscopy Images
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 Noise2Noise on real FMD noisy-image pairs instead of using a traditional VST denoiser | FMD denoising · FMD mixed test set, raw images | PSNR (dB): 32.71 -> 35.40 | Helped |
| Train Noise2Noise without clean-image targets | FMD denoising · FMD mixed test set | PSNR (dB): + almost 2dB | Helped |
| Use Noise2Noise rather than DnCNN | FMD denoising · FMD mixed test set, 1- and 2-image averages | PSNR (dB): 34.88 -> 35.40; 36.02 -> 36.40 | Helped |
| Use Noise2Noise rather than DnCNN | FMD denoising · FMD mixed test set, 16-image average | PSNR (dB): 41.57 -> 41.45 | Hurt |
| Add batch normalization to Noise2Noise (ablation) | Noise2Noise · FMD mixed test set, learning rate 1E-4 | PSNR (dB): 35.40 -> 35.12 | No clear effect |
| Add batch normalization to Noise2Noise (ablation) | Noise2Noise · FMD mixed test set, learning rate 1E-3 | training stability | Helped |
| Use residual learning in DnCNN (ablation) | DnCNN · FMD mixed test set | PSNR (dB) | Helped |
| Vary Noise2Noise learning rate from 1E-3 to 5E-5 (ablation) | Noise2Noise · FMD mixed test set, raw images | PSNR (dB): 34.98 -> 35.49 | Helped |
| Use learning rate 1E-5 instead of 5E-5 (ablation) | Noise2Noise · FMD mixed test set, raw images | PSNR (dB): 35.49 -> 34.65 | Hurt |
| Use learning rate 1E-4 rather than 1E-3 (ablation) | DnCNN · FMD mixed test set, raw images | PSNR (dB): 34.61 -> 34.88 | Helped |
Closest papers by meaning
- Efficient Online Training for Zero-Shot Time-Lapse Microscopy Denoising and Super-Resolution (AAAI 2025 · similarity 0.89)
- scSplit: Bringing Severity Cognizance to Image Decomposition in Fluorescence Microscopy (NeurIPS 2025 · similarity 0.86)
- Volume Tells: Dual Cycle-Consistent Diffusion for 3D Fluorescence Microscopy De-noising and Super-Resolution (CVPR 2025 · similarity 0.86)
- V2V3D: View-to-View Denoised 3D Reconstruction for Light Field Microscopy (CVPR 2025 · similarity 0.85)
- MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays (NeurIPS 2026 · similarity 0.85)
- SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution (NeurIPS 2024 · similarity 0.84)
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.