Physics Constrained Unsupervised Deep Learning for Rapid, High Resolution Scanning Coherent Diffraction Reconstruction
This enables high-resolution real-time imaging for applications like X-ray free electron lasers, addressing a bottleneck in high-throughput scientific fields.
The paper tackled the slow iterative phase recovery in coherent diffractive imaging by proposing an unsupervised physics-informed neural network, PtychoPINN, which achieved a 100-to-1000 times speedup while improving reconstruction quality with a typical 10 dB PSNR increase and 2- to 6-fold linear resolution gain.
By circumventing the resolution limitations of optics, coherent diffractive imaging (CDI) and ptychography are making their way into scientific fields ranging from X-ray imaging to astronomy. Yet, the need for time consuming iterative phase recovery hampers real-time imaging. While supervised deep learning strategies have increased reconstruction speed, they sacrifice image quality. Furthermore, these methods' demand for extensive labeled training data is experimentally burdensome. Here, we propose an unsupervised physics-informed neural network reconstruction method, PtychoPINN, that retains the factor of 100-to-1000 speedup of deep learning-based reconstruction while improving reconstruction quality by combining the diffraction forward map with real-space constraints from overlapping measurements. In particular, PtychoPINN significantly advances generalizability, accuracy (with a typical 10 dB PSNR increase), and linear resolution (2- to 6-fold gain). This blend of performance and speed offers exciting prospects for high-resolution real-time imaging in high-throughput environments such as X-ray free electron lasers (XFELs) and diffraction-limited light sources.