AutoPhaseNN:unsupervised physics-aware deep learning of 3D nanoscale Bragg coherent diffraction imaging

作     者：Yudong Yao Henry Chan Subramanian Sankaranarayanan Prasanna Balaprakash Ross J.Harder Mathew J.Cherukara 

作者机构：Advanced Photon SourceArgonne National LaboratoryLemontIL60439USA Center for Nanoscale MaterialsArgonne National LaboratoryLemontIL60439USA Mathematics and Computer ScienceArgonne National LaboratoryLemontIL60439USA 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2022年第8卷第1期

页      面：1146-1153页

核心收录：

学科分类：070207[理学-光学] 07[理学] 08[工学] 0803[工学-光学工程] 0702[理学-物理学] 

基　　金：This work was performed,in part,at the Advanced Photon Source,a U.S.Department of Energy(DOE)Office of Science User Facility,operated for the DOE Office of Science by Argonne National Laboratory under Contract No.DE-AC02-06CH11357 This research used resources of the Argonne Leadership Computing Facility,which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357 This work was supported by the U.S.Department of Energy,Office of Science,Office of Basic Energy Sciences Data,Artificial Intelligence and Machine Learning at DOE Scientific User Facilities program under Award Number 34532 M.J.C.acknowledges partial support from Argonne LDRD 2021-0090-AutoPtycho:Autonomous,Sparse-sampled Ptychographic Imaging Y.Y.acknowledges partial support from Argonne LDRD 2021-0315-Scalable DL-based 3D X-ray nanoscale imaging enabled by AI accelerators 

主　　题：coherent iterative replace 

摘      要：The problem of phase retrieval underlies various imaging methods from astronomy to nanoscale *** phase retrieval methods are iterative and are therefore computationally *** learning(DL)models have been developed to either provide learned priors or completely replace phase ***,such models require vast amounts of labeled data,which can only be obtained through simulation or performing computationally prohibitive phase retrieval on experimental *** 3D X-ray Bragg coherent diffraction imaging(BCDI)as a representative technique,we demonstrate AutoPhaseNN,a DL-based approach which learns to solve the phase problem without labeled *** incorporating the imaging physics into the DL model during training,AutoPhaseNN learns to invert 3D BCDI data in a single shot without ever being shown real space *** trained,AutoPhaseNN can be effectively used in the 3D BCDI data inversion about 100×faster than iterative phase retrieval methods while providing comparable image quality.