Show simple item record

dc.contributor.authorAlghamdi, Mashealen_US
dc.contributor.authorFu, Qiangen_US
dc.contributor.authorThabet, Alien_US
dc.contributor.authorHeidrich, Wolfgangen_US
dc.contributor.editorBenes, Bedrich and Hauser, Helwigen_US
dc.date.accessioned2021-10-08T07:38:11Z
dc.date.available2021-10-08T07:38:11Z
dc.date.issued2021
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14205
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14205
dc.description.abstractHigh dynamic range (HDR) image acquisition from a single image capture, also known as snapshot HDR imaging, is challenging because the bit depths of camera sensors are far from sufficient to cover the full dynamic range of the scene. Existing HDR techniques focus either on algorithmic reconstruction or hardware modification to extend the dynamic range. In this paper we propose a joint design for snapshot HDR imaging by devising a spatially varying modulation mask in the hardware and building a deep learning algorithm to reconstruct the HDR image. We leverage transfer learning to overcome the lack of sufficiently large HDR datasets available. We show how transferring from a different large‐scale task (image classification on ImageNet) leads to considerable improvements in HDR reconstruction. We achieve a reconfigurable HDR camera design that does not require custom sensors, and instead can be reconfigured between HDR and conventional mode with very simple calibration steps. We demonstrate that the proposed hardware–software so lution offers a flexible yet robust way to modulate per‐pixel exposures, and the network requires little knowledge of the hardware to faithfully reconstruct the HDR image. Comparison results show that our method outperforms the state of the art in terms of visual perception quality.en_US
dc.publisher© 2021 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltden_US
dc.subjecthigh dynamic range/tone mapping
dc.subjectimage and video processing
dc.subjectcomputational photography
dc.titleTransfer Deep Learning for Reconfigurable Snapshot HDR Imaging Using Coded Masksen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersArticles
dc.description.volume40
dc.description.number6
dc.identifier.doi10.1111/cgf.14205
dc.identifier.pages90-103


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record