Show simple item record

dc.contributor.authorSun, Qilin
dc.contributor.authorTseng, Ethan
dc.contributor.authorFu, Qiang
dc.contributor.authorHeidrich, Wolfgang
dc.contributor.authorHeide, Felix
dc.date.accessioned2020-07-13T13:29:10Z
dc.date.available2020-04-15T08:33:54Z
dc.date.available2020-07-13T13:29:10Z
dc.date.issued2020-08-05
dc.identifier.citationSun, Q., Tseng, E., Fu, Q., Heidrich, W., & Heide, F. (2020). Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr42600.2020.00146
dc.identifier.isbn978-1-7281-7169-2
dc.identifier.issn1063-6919
dc.identifier.doi10.1109/CVPR42600.2020.00146
dc.identifier.urihttp://hdl.handle.net/10754/662530
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.
dc.description.sponsorshipThis work was supported by KAUST baseline funding.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/9157825/
dc.relation.urlhttps://ieeexplore.ieee.org/document/9157825/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9157825
dc.rightsArchived with thanks to IEEE
dc.titleLearning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging
dc.typeConference Paper
dc.contributor.departmentComputational Imaging Group
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.conference.date13-19 June 2020
dc.conference.name2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
dc.conference.locationSeattle, WA, USA
dc.eprint.versionPost-print
dc.contributor.institutionPrinceton University
pubs.publication-statusPublished
kaust.personSun, Qilin
kaust.personFu, Qiang
kaust.personHeidrich, Wolfgang
dc.date.accepted2020-02-24
refterms.dateFOA2020-04-15T08:33:54Z
kaust.acknowledged.supportUnitKAUST baseline fund
dc.date.published-online2020-08-05
dc.date.published-print2020-06


Files in this item

Thumbnail
Name:
Sun_Learning_Rank-1_Diffractive_Optics_for_Single-Shot_High_Dynamic_Range_Imaging_CVPR_2020_paper.pdf
Size:
2.863Mb
Format:
PDF
Description:
Open access version
Thumbnail
Name:
02493-supp.pdf
Size:
14.64Mb
Format:
PDF
Description:
supp. material

This item appears in the following Collection(s)

Show simple item record

VersionItemEditorDateSummary

*Selected version