Research map / Image generation / Image restoration
Microscopy Image Restoration with Deep Wiener-Kolmogorov Filters
Valeriya Pronina, Filippos Kokkinos, Dmitry V. Dylov, Stamatios Lefkimmiatis
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| predict regularization kernels per image with a KPN instead of fixed learnable kernels (ablation) | Wiener filter (WF-K) · Gaussian deblurring (noise std 0.001) | PSNR: 35.66 -> 38.72 | Improved |
| predict kernels per pixel (spatially adaptive) instead of per image (ablation) | WF-KPN · Gaussian deblurring (noise std 0.1) | PSNR: 29.20 -> 32.60 | Improved |
| use WF-KPN-SA instead of UNet baseline | UNet · Gaussian deblurring (noise std 0.1) | PSNR: 32.40 -> 32.60 | Improved |
| combine Wiener filter with UNet regularizer gradient (WF-UNet) instead of plain UNet | UNet · Gaussian deblurring (noise std 0.1) | PSNR: 32.40 -> 32.01 | Hurt |
| combine Wiener filter with UNet regularizer gradient (WF-UNet) instead of plain UNet | UNet · Poisson deblurring (peak 1) | PSNR: 28.50 -> 29.04 | Improved |
| increase kernels from 8 of size 3 to 24 of size 5 (ablation) | WF-K · Gaussian deblurring | PSNR: 35.66 -> 35.81 at std 0.001; 29.27 -> 29.21 at std 0.1 | Mixed |
| increase kernels from 8 of size 3 to 24 of size 5 (ablation) | WF-KPN · Gaussian deblurring (noise std 0.001) | PSNR: 38.72 -> 39.95 | Improved |
| increase kernels from 8 of size 3 to 24 of size 5 (ablation) | WF-KPN · Gaussian deblurring (noise std 0.1) | PSNR: 29.20 -> 29.20 | No clear effect |
| use noise-blind WF-KPN-SA versus noise-aware DMSP-NA at very low noise | WF-KPN-SA · Gaussian deblurring (noise std 0.001) | PSNR: 40.44 -> 39.86 | Hurt |
| use spatially adaptive kernels instead of per-image kernels (ablation) | WF-KPN · Runtime 256x256 image (GPU) | time (ms): 7.7 -> 341.4 | Hurt |
Closest papers by meaning
- A Poisson-Gaussian Denoising Dataset With Real Fluorescence Microscopy Images (CVPR 2019 · similarity 0.89)
- Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders (ICLR 2021 · similarity 0.89)
- Efficient Online Training for Zero-Shot Time-Lapse Microscopy Denoising and Super-Resolution (AAAI 2025 · similarity 0.86)
- Stochastic Deep Restoration Priors for Imaging Inverse Problems (ICML 2025 · similarity 0.85)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.85)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.85)
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.
