Simple and practical single-shot digital holography based on unsupervised diffusion model

Single-shot digital holography in Gabor mode offers cost-effective quantitative phase imaging but suffers from the fundamental twin image problem, where real and conjugate images are inherently superimposed, severely limiting phase reconstruction accuracy. Traditional iterative phase retrieval methods require computationally expensive multiple propagations, while off-axis holography demands complex optical setups with precise alignment. We present the first unsupervised diffusion model for automated phase image reconstruction from single-shot in-line holograms, eliminating both twin image artifacts and the need for expensive off-axis configurations. Our framework integrates cycle-consistency and denoising modules to enable training on unpaired hologram-phase image datasets, learning the mapping between low-cost in-line measurements and high-quality phase distributions without requiring labeled data pairs. Comprehensive evaluation on diverse biological specimens demonstrates that our approach significantly outperforms conventional unsupervised methods, achieving superior Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values for both red blood cells and cancer cells. Critically, the model maintains exceptional performance even with limited training data, consistently outperforming supervised learning approaches under data-constrained conditions. The framework exhibits remarkable generalization capabilities, successfully reconstructing phase images from holograms captured at different propagation distances and processing various cancer cell types not included in training data. This computational breakthrough enables accurate, scalable, and hardware-efficient quantitative phase imaging, democratizing access to high-quality phase microscopy for resource-constrained environments while maintaining reconstruction fidelity comparable to complex off-axis systems.