Research map / Image generation / Image restoration
Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
Rui Li, Mikhail Kudryashev, Artur Yakimovich
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 |
|---|---|---|---|
| use multi-stage residual BCR (m-rBCR) instead of single-stage s-rBCR (ablation) | residual BCR net · BioSR (simulated widefield) | PSNR (dB): 20.28 -> 24.89 | Improved |
| use multi-stage instead of single-stage (ablation) | residual BCR net · Widefield-confocal (real) | PSNR (dB): 17.67 -> 23.10 | Improved |
| multi-stage instead of single-stage (ablation) | residual BCR net · BioSR runtime | runtime (s): 0.0019 -> 0.0036 | Hurt |
| use m-rBCR instead of MIMO-U-Net | microscopy deconvolution · BioSR (simulated widefield) | PSNR (dB): 23.95 -> 24.89 | Improved |
| use m-rBCR instead of MIMO-U-Net | microscopy deconvolution · ImageNet (simulated widefield) | PSNR (dB): 22.35 -> 21.41 | Hurt |
| use m-rBCR instead of MIMO-U-Net on real dSTORM data | microscopy deconvolution · dSTORM (real) | PSNR (dB): 18.91 -> 20.13 | Improved |
| use physics-informed BCR network instead of explicit Richardson-Lucy | microscopy deconvolution · BioSR (simulated widefield) | PSNR (dB): 13.39 -> 24.89 | Improved |
| increase decomposition level K beyond 12 (ablation) | m-rBCR · BioSR (simulated widefield) | PSNR | Hurt |
| increase residual block depth RDN beyond 7 (ablation) | m-rBCR · BioSR (simulated widefield) | PSNR | No clear effect |
Closest papers by meaning
- High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction (TPAMI 2019 · similarity 0.86)
- V2V3D: View-to-View Denoised 3D Reconstruction for Light Field Microscopy (CVPR 2025 · similarity 0.86)
- Zero-Shot Learning for Limited Photon Budget Denoising in Structured Illumination Microscopy (TPAMI 2025 · similarity 0.86)
- OpticalNet: An Optical Imaging Dataset and Benchmark Beyond the Diffraction Limit (CVPR 2025 · similarity 0.85)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · similarity 0.85)
- Efficient Online Training for Zero-Shot Time-Lapse Microscopy Denoising and Super-Resolution (AAAI 2025 · 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.
