Modern High Dynamic Range Imaging at the Time of Deep Learning

dc.contributor.authorBanterle, Francescoen_US
dc.contributor.authorArtusi, Alessandroen_US
dc.contributor.editorSerrano, Anaen_US
dc.contributor.editorSlusallek, Philippen_US
dc.date.accessioned2023-05-03T05:58:05Z
dc.date.available2023-05-03T05:58:05Z
dc.date.issued2023
dc.description.abstractIn this tutorial, we introduce how the High Dynamic Range (HDR) imaging field has evolved in this new era where machine learning approaches have become dominant. The main reason of this success is that the use of machine learning and deep learning have automatized many tedious tasks achieving high-quality results overperforming classic methods. After an introduction on classic HDR imaging and its open problem, we will summarize the main approaches for: merging of multiple exposures, single image reconstructions or inverse tone mapping, tone mapping, and display visualization. Finally, we will highlights the still open problems in this machine learning era, and possible direction on how to solve them.en_US
dc.description.sectionheadersTutorials
dc.description.seriesinformationEurographics 2023 - Tutorials
dc.identifier.doi10.2312/egt.20231033
dc.identifier.isbn978-3-03868-212-7
dc.identifier.issn1017-4656
dc.identifier.pages15-19
dc.identifier.pages5 pages
dc.identifier.urihttps://doi.org/10.2312/egt.20231033
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egt20231033
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleModern High Dynamic Range Imaging at the Time of Deep Learningen_US
Files
Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
015-019.pdf
Size:
378.41 KB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
tut1003_slides.pdf
Size:
98.69 MB
Format:
Adobe Portable Document Format