Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Miller, Markus | |
dc.contributor.author | Nischwitz, Alfred | |
dc.contributor.author | Westermann, Rüdiger | |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2021-08-31T05:45:53Z | - |
dc.date.available | 2021-08-31T05:45:53Z | - |
dc.date.issued | 2021 | |
dc.identifier.citation | WSCG 2021: full papers proceedings: 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 31-40. | en |
dc.identifier.isbn | 978-80-86943-34-3 | |
dc.identifier.issn | 2464-4617 | |
dc.identifier.issn | 2464–4625(CD/DVD) | |
dc.identifier.uri | http://hdl.handle.net/11025/45007 | |
dc.format | 10 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Václav Skala - UNION Agency | cs |
dc.rights | © Václav Skala - UNION Agency | cs |
dc.subject | světlo | cs |
dc.subject | zdroj | cs |
dc.subject | směr | cs |
dc.subject | odhad | cs |
dc.subject | rekonstrukce | cs |
dc.subject | RGB | cs |
dc.subject | hluboké učení | cs |
dc.title | Deep Light Direction Reconstruction from single RGB images | en |
dc.type | konferenční příspěvek | cs |
dc.type | conferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | In augmented reality applications, consistent illumination between virtual and real objects is important for creatingan immersive user experience. Consistent illumination can be achieved by appropriate parameterisation of thevirtual illumination model, that is consistent with real-world lighting conditions. In this study, we developed amethod to reconstruct the general light direction from red-green-blue (RGB) images of real-world scenes using amodified VGG-16 neural network. We reconstructed the general light direction as azimuth and elevation angles. Toavoid inaccurate results caused by coordinate uncertainty occurring at steep elevation angles, we further introducedstereographically projected coordinates. Unlike recent deep-learning-based approaches for reconstructing the lightsource direction, our approach does not require depth information and thus does not rely on special red-green-blue-depth (RGB-D) images as input. | en |
dc.subject.translated | light | en |
dc.subject.translated | source | en |
dc.subject.translated | direction | en |
dc.subject.translated | estimation | en |
dc.subject.translated | reconstruction | en |
dc.subject.translated | RGB | en |
dc.subject.translated | deep learning | en |
dc.identifier.doi | https://doi.org/10.24132/CSRN.2021.3101.4 | |
dc.type.status | Peer-reviewed | en |
Vyskytuje se v kolekcích: | WSCG 2021: Full Papers Proceedings |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
H59.pdf | Plný text | 7,5 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/45007
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.