Real-time Light Estimation and Neural Soft Shadows for AR Indoor Scenarios

dc.contributor.authorSommer, Alexander
dc.contributor.authorSchwanecke, Ulrich
dc.contributor.authorSchoemer, Elmar
dc.contributor.editorSkala, Václav
dc.date.accessioned2023-10-03T15:43:19Z
dc.date.available2023-10-03T15:43:19Z
dc.date.issued2023
dc.description.abstract-translatedWe present a pipeline for realistic embedding of virtual objects into footage of indoor scenes with focus on real-time AR applications. Our pipeline consists of two main components: A light estimator and a neural soft shadow texture generator. Our light estimation is based on deep neural nets and determines the main light direction, light color, ambient color and an opacity parameter for the shadow texture. Our neural soft shadow method encodes object-based realistic soft shadows as light direction dependent textures in a small MLP. We show that our pipeline can be used to integrate objects into AR scenes in a new level of realism in real-time. Our models are small enough to run on current mobile devices. We achieve runtimes of 9ms for light estimation and 5ms for neural shadows on an iPhone 11 Pro.en
dc.format9 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationJournal of WSCG. 2023, vol. 31, no. 1-2, p. 71-79.en
dc.identifier.doihttps://www.doi.org/10.24132/JWSCG.2023.8
dc.identifier.issn1213 – 6972 (hard copy)
dc.identifier.issn1213 – 6980 (CD-ROM)
dc.identifier.issn1213 – 6964 (on-line)
dc.identifier.urihttp://hdl.handle.net/11025/54286
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencyen
dc.rights© Václav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectrozšířená realitacs
dc.subjectlehký odhadcs
dc.subjectvykreslování stínůcs
dc.subjectneurální měkké stínycs
dc.subject.translatedaugmented realityen
dc.subject.translatedlight estimationen
dc.subject.translatedshadow renderingen
dc.subject.translatedneural soft shadowsen
dc.titleReal-time Light Estimation and Neural Soft Shadows for AR Indoor Scenariosen
dc.typečlánekcs
dc.typearticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
!_2023-Journal_WSCG-81-89.pdf
Size:
7.82 MB
Format:
Adobe Portable Document Format
Description:
Plný text
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: