Neural Architecture Search Generated Phase Retrieval Net for Real-Time Off-Axis Quantitative Phase Imaging
Saved in:
| Title: | Neural Architecture Search Generated Phase Retrieval Net for Real-Time Off-Axis Quantitative Phase Imaging |
|---|---|
| Authors: | Xin Shu, Mengxuan Niu, Yi Zhang, Wei Luo, Renjie Zhou |
| Source: | IEEE Photonics Technology Letters. 37:1069-1072 |
| Publication Status: | Preprint |
| Publisher Information: | Institute of Electrical and Electronics Engineers (IEEE), 2025. |
| Publication Year: | 2025 |
| Subject Terms: | Machine Learning, FOS: Computer and information sciences, Image and Video Processing (eess.IV), FOS: Electrical engineering, electronic engineering, information engineering, Image and Video Processing, Machine Learning (cs.LG) |
| Description: | In off-axis Quantitative Phase Imaging (QPI), artificial neural networks have been recently applied for phase retrieval with aberration compensation and phase unwrapping. However, the involved neural network architectures are largely unoptimized and inefficient with low inference speed, which hinders the realization of real-time imaging. Here, we propose a Neural Architecture Search (NAS) generated Phase Retrieval Net (NAS-PRNet) for accurate and fast phase retrieval. NAS-PRNet is an encoder-decoder style neural network, automatically found from a large neural network architecture search space through NAS. By modifying the differentiable NAS scheme from SparseMask, we learn the optimized skip connections through gradient descent. Specifically, we implement MobileNet-v2 as the encoder and define a synthesized loss that incorporates phase reconstruction loss and network sparsity loss. NAS-PRNet has achieved high-fidelity phase retrieval by achieving a peak Signal-to-Noise Ratio (PSNR) of 36.7 dB and a Structural SIMilarity (SSIM) of 86.6% as tested on interferograms of biological cells. Notably, NAS-PRNet achieves phase retrieval in only 31 ms, representing 15x speedup over the most recent Mamba-UNet with only a slightly lower phase retrieval accuracy. |
| Document Type: | Article |
| ISSN: | 1941-0174 1041-1135 |
| DOI: | 10.1109/lpt.2025.3581063 |
| DOI: | 10.48550/arxiv.2210.14231 |
| Access URL: | http://arxiv.org/abs/2210.14231 |
| Rights: | CC BY NC ND |
| Accession Number: | edsair.doi.dedup.....c67cc2c55b5e90dfa3ea4e556b1d5e73 |
| Database: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | In off-axis Quantitative Phase Imaging (QPI), artificial neural networks have been recently applied for phase retrieval with aberration compensation and phase unwrapping. However, the involved neural network architectures are largely unoptimized and inefficient with low inference speed, which hinders the realization of real-time imaging. Here, we propose a Neural Architecture Search (NAS) generated Phase Retrieval Net (NAS-PRNet) for accurate and fast phase retrieval. NAS-PRNet is an encoder-decoder style neural network, automatically found from a large neural network architecture search space through NAS. By modifying the differentiable NAS scheme from SparseMask, we learn the optimized skip connections through gradient descent. Specifically, we implement MobileNet-v2 as the encoder and define a synthesized loss that incorporates phase reconstruction loss and network sparsity loss. NAS-PRNet has achieved high-fidelity phase retrieval by achieving a peak Signal-to-Noise Ratio (PSNR) of 36.7 dB and a Structural SIMilarity (SSIM) of 86.6% as tested on interferograms of biological cells. Notably, NAS-PRNet achieves phase retrieval in only 31 ms, representing 15x speedup over the most recent Mamba-UNet with only a slightly lower phase retrieval accuracy. |
|---|---|
| ISSN: | 19410174 10411135 |
| DOI: | 10.1109/lpt.2025.3581063 |