Research map / Image generation / Image restoration
LWGNet – Learned Wirtinger Gradients for Fourier Ptychographic Phase Retrieval
Atreyee Saha, Salman S. Khan, Sagar Sehrawat, Sanjana S. Prabhu, Shanti Bhattacharya, Kaushik Mitra
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 complex-valued operations instead of real-valued operations on real and imaginary channels (ablation) | LWGNet · simulated data | average PSNR: increases the average PSNR by ~5dB | Improved |
| process stochastic gradients with the learned network instead of enhancing the object field after Wirtinger updates (ablation) | LWGNet · simulated data | reconstruction quality | Improved |
| use stochastic gradients instead of regular gradients (ablation) | LWGNet · simulated data | reconstruction quality | Improved |
| increase unrolled stages from 3 to 5 for 8-bit data (ablation) | LWGNet · simulated 8-bit | PSNR: 3 stages -> 5 stages | Improved |
| increase unrolled stages beyond 3 for 16-bit and 12-bit data (ablation) | LWGNet · simulated 16-bit and 12-bit | PSNR: saturates after 3 stages | No clear effect |
| use LWGNet instead of F-cGAN at 8-bit | LWGNet · Simulated FPM histology (8-bit) | PSNR: 25.715 -> 26.035 | Improved |
| use LWGNet instead of F-cGAN at 12-bit | LWGNet · Simulated FPM histology (12-bit) | PSNR: 26.325 -> 27.726 | Improved |
| use LWGNet instead of F-cGAN at 16-bit | LWGNet · Simulated FPM histology (16-bit) | PSNR: 29.021 -> 28.745 | Hurt |
| use LWGNet instead of F-cGAN at 16-bit | LWGNet · Simulated FPM histology (16-bit) | SSIM: 0.907 -> 0.829 | Hurt |
| use LWGNet instead of F-cGAN in parameters | LWGNet · Simulated FPM histology | parameters (millions): 7.88 -> 0.39 | Improved |
| use LWGNet instead of F-cGAN in inference time | LWGNet · Simulated FPM histology | inference time (ms): 29 -> 341 | Hurt |
| use naive unrolled Wirtinger flow with convolution block (ablation) | naive unrolled WF · simulated data | convergence | Hurt |
Closest papers by meaning
- FourierNets enable the design of highly non-local optical encoders for computational imaging (NeurIPS 2022 · similarity 0.84)
- OpticalNet: An Optical Imaging Dataset and Benchmark Beyond the Diffraction Limit (CVPR 2025 · similarity 0.82)
- V2V3D: View-to-View Denoised 3D Reconstruction for Light Field Microscopy (CVPR 2025 · similarity 0.82)
- From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy (NeurIPS 2025 · similarity 0.82)
- Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting (NeurIPS 2024 · similarity 0.82)
- Single Exposure Quantitative Phase Imaging with a Conventional Microscope Using Diffusion Models (AAAI 2025 · similarity 0.81)
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.
