Skip to main content

Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging

Author(s): Sun, Qilin; Tseng, Ethan; Fu, Qiang; Heidrich, Wolfgang; Heide, Felix

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr11n8k
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSun, Qilin-
dc.contributor.authorTseng, Ethan-
dc.contributor.authorFu, Qiang-
dc.contributor.authorHeidrich, Wolfgang-
dc.contributor.authorHeide, Felix-
dc.date.accessioned2021-10-08T19:46:51Z-
dc.date.available2021-10-08T19:46:51Z-
dc.date.issued2020en_US
dc.identifier.citationSun, Qilin, Ethan Tseng, Qiang Fu, Wolfgang Heidrich, and Felix Heide. "Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020): pp. 1383-1393. doi:10.1109/CVPR42600.2020.00146en_US
dc.identifier.issn1063-6919-
dc.identifier.urihttps://openaccess.thecvf.com/content_CVPR_2020/papers/Sun_Learning_Rank-1_Diffractive_Optics_for_Single-Shot_High_Dynamic_Range_Imaging_CVPR_2020_paper.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr11n8k-
dc.description.abstractHigh-dynamic range (HDR) imaging is an essential imaging modality for a wide range of applications in uncontrolled environments, including autonomous driving, robotics, and mobile phone cameras. However, existing HDR techniques in commodity devices struggle with dynamic scenes due to multi-shot acquisition and post-processing time, e.g. mobile phone burst photography, making such approaches unsuitable for real-time applications. In this work, we propose a method for snapshot HDR imaging by learning an optical HDR encoding in a single image which maps saturated highlights into neighboring unsaturated areas using a diffractive optical element (DOE). We propose a novel rank-1 parameterization of the proposed DOE which avoids vast trainable parameters and keeps high frequencies' encoding compared with conventional end-to-end design methods. We further propose a reconstruction network tailored to this rank-1 parametrization for recovery of clipped information from the encoded measurements. The proposed end-to-end framework is validated through simulation and real-world experiments and improves the PSNR by more than 7 dB over state-of-the-art end-to-end designs.en_US
dc.format.extent1383 - 1393en_US
dc.language.isoen_USen_US
dc.relation.ispartofIEEE/CVF Conference on Computer Vision and Pattern Recognitionen_US
dc.rightsAuthor's manuscripten_US
dc.titleLearning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imagingen_US
dc.typeConference Articleen_US
dc.identifier.doi10.1109/CVPR42600.2020.00146-
dc.identifier.eissn2575-7075-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
DiffractiveOpticsSingleShotHighDynamicRangeImaging.pdf2.93 MBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.