Show simple item record

dc.contributor.authorEilertsen, Gen
dc.contributor.authorKronander, Jen
dc.contributor.authorDenes, Gen
dc.contributor.authorMantiuk, Rafalen
dc.contributor.authorUnger, Jen
dc.date.accessioned2018-06-25T14:09:54Z
dc.date.available2018-06-25T14:09:54Z
dc.date.issued2017-11-20en
dc.identifier.issn0730-0301
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/277485
dc.description.abstractCamera sensors can only capture a limited range of luminance simultane- ously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combined. In this paper we address the problem of predicting information that have been lost in saturated image ar- eas, in order to enable HDR reconstruction from a single exposure.We show that this problem is well-suited for deep learning algorithms, and propose a deep convolutional neural network (CNN) that is specifically designed taking into account the challenges in predicting HDR values. To train the CNN we gather a large dataset of HDR images, which we augment by simulating sensor saturation for a range of cameras. To further boost robustness, we pre-train the CNN on a simulated HDR dataset created from a subset of the MIT Places database.We demonstrate that our approach can reconstruct high-resolution visually convincing HDR results in a wide range of situa- tions, and that it generalizes well to reconstruction of images captured with arbitrary and low-end cameras that use unknown camera response func- tions and post-processing. Furthermore, we compare to existing methods for HDR expansion, and show high quality results also for image based lighting. Finally, we evaluate the results in a subjective experiment performed on an HDR display. This shows that the reconstructed HDR images are visually convincing, with large improvements as compared to existing methods.
dc.titleHDR image reconstruction from a single exposure using deep CNNsen
dc.typeArticle
prism.issueIdentifier6en
prism.publicationDate2017en
prism.publicationNameACM Transactions on Graphicsen
prism.volume36en
dc.identifier.doi10.17863/CAM.18699
dcterms.dateAccepted2017-09-08en
rioxxterms.versionofrecord10.1145/3130800.3130816en
rioxxterms.versionAM*
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2017-11-20en
dc.contributor.orcidMantiuk, Rafal [0000-0003-2353-0349]
dc.identifier.eissn1557-7368
rioxxterms.typeJournal Article/Reviewen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record