DRHDR: A Dual branch Residual Network for Multi-Bracket High Dynamic Range Imaging

Juan Marin-Vega, Michael Sloth, Peter Schneider-Kamp, Richard Rottger

Publikation: Bidrag til tidsskriftKonferenceartikelForskningpeer review

Abstrakt

We introduce DRHDR, a Dual branch Residual Convolutional Neural Network for Multi-Bracket HDR Imaging. To address the challenges of fusing multiple brackets from dynamic scenes, we propose an efficient dual branch network that operates on two different resolutions. The full resolution branch uses a Deformable Convolutional Block to align features and retain high-frequency details. A low resolution branch with a Spatial Attention Block aims to attend wanted areas from the non-reference brackets, and suppress displaced features that could incur on ghosting artifacts. By using a dual branch approach we are able to achieve high quality results while constraining the computational resources required to estimate the HDR results.

OriginalsprogEngelsk
TidsskriftIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Sider (fra-til)843-851
Antal sider9
ISSN2160-7508
DOI
StatusUdgivet - 2022
Begivenhed2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 - New Orleans, USA
Varighed: 19. jun. 202220. jun. 2022

Konference

Konference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
Land/OmrådeUSA
ByNew Orleans
Periode19/06/202220/06/2022

Bibliografisk note

Publisher Copyright:
© 2022 IEEE.

Fingeraftryk

Dyk ned i forskningsemnerne om 'DRHDR: A Dual branch Residual Network for Multi-Bracket High Dynamic Range Imaging'. Sammen danner de et unikt fingeraftryk.

Citationsformater