Název:	Deep Light Direction Reconstruction from single RGB images
Autoři:	Miller, Markus Nischwitz, Alfred Westermann, Rüdiger
Citace zdrojového dokumentu:	WSCG 2021: full papers proceedings: 29. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 31-40.
Datum vydání:	2021
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	konferenční příspěvek conferenceObject
URI:	http://hdl.handle.net/11025/45007
ISBN:	978-80-86943-34-3
ISSN:	2464-4617 2464–4625(CD/DVD)
Klíčová slova:	světlo;zdroj;směr;odhad;rekonstrukce;RGB;hluboké učení
Klíčová slova v dalším jazyce:	light;source;direction;estimation;reconstruction;RGB;deep learning
Abstrakt v dalším jazyce:	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.
Práva:	© Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	WSCG 2021: Full Papers Proceedings

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.