Skip to main content

Research Repository

Advanced Search

ExpandNet: A deep convolutional neural network for high dynamic range expansion from low dynamic range content

Marnerides, Demetris; Bashford-Rogers, Thomas; Hatchett, Jon; Debattista, Kurt

ExpandNet: A deep convolutional neural network for high dynamic range expansion from low dynamic range content Thumbnail


Authors

Demetris Marnerides

Jon Hatchett

Kurt Debattista



Abstract

© 2018 The Author(s) and 2018 The Eurographics Association and John Wiley & Sons Ltd. High dynamic range (HDR) imaging provides the capability of handling real world lighting as opposed to the traditional low dynamic range (LDR) which struggles to accurately represent images with higher dynamic range. However, most imaging content is still available only in LDR. This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet. ExpandNet accepts LDR images as input and generates images with an expanded range in an end-to-end fashion. The model attempts to reconstruct missing information that was lost from the original signal due to quantization, clipping, tone mapping or gamma correction. The added information is reconstructed from learned features, as the network is trained in a supervised fashion using a dataset of HDR images. The approach is fully automatic and data driven; it does not require any heuristics or human expertise. ExpandNet uses a multiscale architecture which avoids the use of upsampling layers to improve image quality. The method performs well compared to expansion/inverse tone mapping operators quantitatively on multiple metrics, even for badly exposed inputs.

Citation

Marnerides, D., Bashford-Rogers, T., Hatchett, J., & Debattista, K. (2018). ExpandNet: A deep convolutional neural network for high dynamic range expansion from low dynamic range content. Computer Graphics Forum, 37(2), 37-49. https://doi.org/10.1111/cgf.13340

Journal Article Type Article
Acceptance Date Feb 9, 2018
Online Publication Date May 22, 2018
Publication Date May 22, 2018
Deposit Date Apr 23, 2018
Publicly Available Date May 23, 2019
Journal Computer Graphics Forum
Print ISSN 0167-7055
Electronic ISSN 1467-8659
Publisher Wiley
Peer Reviewed Peer Reviewed
Volume 37
Issue 2
Pages 37-49
DOI https://doi.org/10.1111/cgf.13340
Keywords deep learning, inverse tone mapping, HDR
Public URL https://uwe-repository.worktribe.com/output/867544
Publisher URL https://doi.org/10.1111/cgf.13340
Additional Information Additional Information : This is the peer reviewed version of the following article: [Marnerides, D., Bashford-Rogers, T., Hatchett, J. and Debattista, K. (2018) ExpandNet: A deep convolutional neural network for high dynamic range expansion from low dynamic range content. Computer Graphics Forum, 37 (2). pp. 37-49. ISSN 0167-7055], which has been published in final form at https://doi.org/10.1111/cgf.13340. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving

Files







You might also like



Downloadable Citations