Enhancement of Partially Coherent Diffractive Images Using Generative Adversarial Network
We present a deep learning-based generative model for the enhancement of partially coherent diffractive images. In lensless coherent diffractive imaging, a highly coherent X-ray illumination is required to image an object at high resolution. Non-ideal experimental conditions result in a partially co...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/3/2/17 |
| _version_ | 1797490793684926464 |
|---|---|
| author | Jong Woo Kim Marc Messerschmidt William S. Graves |
| author_facet | Jong Woo Kim Marc Messerschmidt William S. Graves |
| author_sort | Jong Woo Kim |
| collection | DOAJ |
| description | We present a deep learning-based generative model for the enhancement of partially coherent diffractive images. In lensless coherent diffractive imaging, a highly coherent X-ray illumination is required to image an object at high resolution. Non-ideal experimental conditions result in a partially coherent X-ray illumination, lead to imperfections of coherent diffractive images recorded on a detector, and ultimately limit the capability of lensless coherent diffractive imaging. The previous approaches, relying on the coherence property of illumination, require preliminary experiments or expensive computations. In this article, we propose a generative adversarial network (GAN) model to enhance the visibility of fringes in partially coherent diffractive images. Unlike previous approaches, the model is trained to restore the latent sharp features from blurred input images without finding coherence properties of illumination. We demonstrate that the GAN model performs well with both coherent diffractive imaging and ptychography. It can be applied to a wide range of imaging techniques relying on phase retrieval of coherent diffraction patterns. |
| first_indexed | 2024-03-10T00:38:09Z |
| format | Article |
| id | doaj.art-331f3985fd1248a897e4cd989bb0b84d |
| institution | Directory Open Access Journal |
| issn | 2673-2688 |
| language | English |
| last_indexed | 2024-03-10T00:38:09Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj.art-331f3985fd1248a897e4cd989bb0b84d2023-11-23T15:12:33ZengMDPI AGAI2673-26882022-04-013227428410.3390/ai3020017Enhancement of Partially Coherent Diffractive Images Using Generative Adversarial NetworkJong Woo Kim0Marc Messerschmidt1William S. Graves2Biodesign Beus CXFEL Laboratory, Arizona State University, Tempe, AZ 85281, USABiodesign Beus CXFEL Laboratory, Arizona State University, Tempe, AZ 85281, USABiodesign Beus CXFEL Laboratory, Arizona State University, Tempe, AZ 85281, USAWe present a deep learning-based generative model for the enhancement of partially coherent diffractive images. In lensless coherent diffractive imaging, a highly coherent X-ray illumination is required to image an object at high resolution. Non-ideal experimental conditions result in a partially coherent X-ray illumination, lead to imperfections of coherent diffractive images recorded on a detector, and ultimately limit the capability of lensless coherent diffractive imaging. The previous approaches, relying on the coherence property of illumination, require preliminary experiments or expensive computations. In this article, we propose a generative adversarial network (GAN) model to enhance the visibility of fringes in partially coherent diffractive images. Unlike previous approaches, the model is trained to restore the latent sharp features from blurred input images without finding coherence properties of illumination. We demonstrate that the GAN model performs well with both coherent diffractive imaging and ptychography. It can be applied to a wide range of imaging techniques relying on phase retrieval of coherent diffraction patterns.https://www.mdpi.com/2673-2688/3/2/17partial coherencecoherent diffractive imagingGAN (generative adversarial network)phase retrievalptychography |
| spellingShingle | Jong Woo Kim Marc Messerschmidt William S. Graves Enhancement of Partially Coherent Diffractive Images Using Generative Adversarial Network AI partial coherence coherent diffractive imaging GAN (generative adversarial network) phase retrieval ptychography |
| title | Enhancement of Partially Coherent Diffractive Images Using Generative Adversarial Network |
| title_full | Enhancement of Partially Coherent Diffractive Images Using Generative Adversarial Network |
| title_fullStr | Enhancement of Partially Coherent Diffractive Images Using Generative Adversarial Network |
| title_full_unstemmed | Enhancement of Partially Coherent Diffractive Images Using Generative Adversarial Network |
| title_short | Enhancement of Partially Coherent Diffractive Images Using Generative Adversarial Network |
| title_sort | enhancement of partially coherent diffractive images using generative adversarial network |
| topic | partial coherence coherent diffractive imaging GAN (generative adversarial network) phase retrieval ptychography |
| url | https://www.mdpi.com/2673-2688/3/2/17 |
| work_keys_str_mv | AT jongwookim enhancementofpartiallycoherentdiffractiveimagesusinggenerativeadversarialnetwork AT marcmesserschmidt enhancementofpartiallycoherentdiffractiveimagesusinggenerativeadversarialnetwork AT williamsgraves enhancementofpartiallycoherentdiffractiveimagesusinggenerativeadversarialnetwork |