Consistent Multi- and Single-View HDR-Image Reconstruction from Single Exposures

Simple item page
dc.contributor.authorMohan, Adityaen_US
dc.contributor.authorZhang, Jingen_US
dc.contributor.authorCozot, Rémien_US
dc.contributor.authorLoscos, Celineen_US
dc.contributor.editorSauvage, Basileen_US
dc.contributor.editorHasic-Telalovic, Jasminkaen_US
dc.date.accessioned2022-04-22T07:54:24Z
dc.date.available2022-04-22T07:54:24Z
dc.date.issued2022
dc.description.abstractWe propose a CNN-based approach for reconstructing HDR images from just a single exposure. It predicts the saturated areas of LDR images and then blends the linearized input with the predicted outputs. Two loss functions are used: the Mean Absolute Error and the Multi-Scale Structural Similarity Index. The choice of these loss functions allows us to outperform previous algorithms in the reconstructed dynamic range. Once the network trained, we input multi-view images to it to output multi-view coherent images.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEurographics 2022 - Posters
dc.identifier.doi10.2312/egp.20221004
dc.identifier.isbn978-3-03868-171-7
dc.identifier.issn1017-4656
dc.identifier.pages11-12
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/egp.20221004
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/egp20221004
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleConsistent Multi- and Single-View HDR-Image Reconstruction from Single Exposuresen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
011-012.pdf
Size:
2.54 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
poster1005_poster_pdf.pdf
Size:
905.54 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
poster1005_video.mp4
Size:
80.12 MB
Format:
Unknown data format
Download
Collections
EG 2022 - Posters