001048804 001__ 1048804
001048804 005__ 20251217202227.0
001048804 0247_ $$2doi$$a10.48550/ARXIV.2511.07633
001048804 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-04917
001048804 037__ $$aFZJ-2025-04917
001048804 1001_ $$0P:(DE-Juel1)184644$$aBangun, Arya$$b0$$ufzj
001048804 245__ $$aFlowTIE: Flow-based Transport of Intensity Equation for Phase Gradient Estimation from 4D-STEM Data
001048804 260__ $$barXiv$$c2025
001048804 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1765992836_12985
001048804 3367_ $$2ORCID$$aWORKING_PAPER
001048804 3367_ $$028$$2EndNote$$aElectronic Article
001048804 3367_ $$2DRIVER$$apreprint
001048804 3367_ $$2BibTeX$$aARTICLE
001048804 3367_ $$2DataCite$$aOutput Types/Working Paper
001048804 520__ $$aWe introduce FlowTIE, a neural-network-based framework for phase reconstruction from 4D-Scanning Transmission Electron Microscopy (STEM) data, which integrates the Transport of Intensity Equation (TIE) with a flow-based representation of the phase gradient. This formulation allows the model to bridge data-driven learning with physics-based priors, improving robustness under dynamical scattering conditions for thick specimen. The validation on simulated datasets of crystalline materials, benchmarking to classical TIE and gradient-based optimization methods are presented. The results demonstrate that FlowTIE improves phase reconstruction accuracy, fast, and can be integrated with a thick specimen model, namely multislice method.
001048804 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001048804 588__ $$aDataset connected to DataCite
001048804 650_7 $$2Other$$aMachine Learning (cs.LG)
001048804 650_7 $$2Other$$aFOS: Computer and information sciences
001048804 7001_ $$0P:(DE-HGF)0$$aTöllner, Maximilian$$b1
001048804 7001_ $$0P:(DE-Juel1)200005$$aZhao, Xuan$$b2$$ufzj
001048804 7001_ $$0P:(DE-HGF)0$$aKübel, Christian$$b3
001048804 7001_ $$0P:(DE-Juel1)129394$$aScharr, Hanno$$b4$$ufzj
001048804 773__ $$a10.48550/ARXIV.2511.07633
001048804 8564_ $$uhttps://juser.fz-juelich.de/record/1048804/files/2511.07633v1.pdf$$yOpenAccess
001048804 909CO $$ooai:juser.fz-juelich.de:1048804$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001048804 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)184644$$aForschungszentrum Jülich$$b0$$kFZJ
001048804 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)200005$$aForschungszentrum Jülich$$b2$$kFZJ
001048804 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129394$$aForschungszentrum Jülich$$b4$$kFZJ
001048804 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001048804 9141_ $$y2025
001048804 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001048804 920__ $$lyes
001048804 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001048804 980__ $$apreprint
001048804 980__ $$aVDB
001048804 980__ $$aUNRESTRICTED
001048804 980__ $$aI:(DE-Juel1)IAS-8-20210421
001048804 9801_ $$aFullTexts