Conditional Injective Flows for Bayesian Imaging

Simple item page
dc.citation.firstpage224en_US
dc.citation.journalTitleIEEE Transactions on Computational Imagingen_US
dc.citation.lastpage237en_US
dc.citation.volumeNumber9en_US
dc.contributor.authorKhorashadizadeh, AmirEhsanen_US
dc.contributor.authorKothari, Koniken_US
dc.contributor.authorSalsi, Leonardoen_US
dc.contributor.authorHarandi, Ali Aghababaeien_US
dc.contributor.authorde Hoop, Maartenen_US
dc.contributor.authorDokmanić, Ivanen_US
dc.date.accessioned2023-03-23T14:10:32Zen_US
dc.date.available2023-03-23T14:10:32Zen_US
dc.date.issued2023en_US
dc.description.abstractMost deep learning models for computational imaging regress a single reconstructed image. In practice, however, ill-posedness, nonlinearity, model mismatch, and noise often conspire to make such point estimates misleading or insufficient. The Bayesian approach models images and (noisy) measurements as jointly distributed random vectors and aims to approximate the posterior distribution of unknowns. Recent variational inference methods based on conditional normalizing flows are a promising alternative to traditional MCMC methods, but they come with drawbacks: excessive memory and compute demands for moderate to high resolution images and underwhelming performance on hard nonlinear problems. In this work, we propose C-Trumpets—conditional injective flows specifically designed for imaging problems, which greatly diminish these challenges. Injectivity reduces memory footprint and training time while low-dimensional latent space together with architectural innovations like fixed-volume-change layers and skip-connection revnet layers, C-Trumpets outperform regular conditional flow models on a variety of imaging and image restoration tasks, including limited-view CT and nonlinear inverse scattering, with a lower compute and memory budget. C-Trumpets enable fast approximation of point estimates like MMSE or MAP as well as physically-meaningful uncertainty quantification.en_US
dc.identifier.citationKhorashadizadeh, AmirEhsan, Kothari, Konik, Salsi, Leonardo, et al.. "Conditional Injective Flows for Bayesian Imaging." <i>IEEE Transactions on Computational Imaging,</i> 9, (2023) IEEE: 224-237. https://doi.org/10.1109/TCI.2023.3248949.en_US
dc.identifier.digitalConditional_Injective_Flows_for_Bayesian_Imagingen_US
dc.identifier.doihttps://doi.org/10.1109/TCI.2023.3248949en_US
dc.identifier.urihttps://hdl.handle.net/1911/114523en_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.rightsThis work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/en_US
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en_US
dc.titleConditional Injective Flows for Bayesian Imagingen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Conditional_Injective_Flows_for_Bayesian_Imaging.pdf
Size:
4.61 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
CMOR Publications