Physically‐Based Lighting for 3D Generative Models of Cars

Recent work has demonstrated that Generative Adversarial Networks (GANs) can be trained to generate 3D content from 2D image collections, by synthesizing features for neural radiance field rendering. However, most such solutions generate radiance, with lighting entangled with materials. This results...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computer graphics forum 2024-05, Vol.43 (2), p.n/a
Hauptverfasser:	Violante, N., Gauthier, A., Diolatzis, S., Leimkühler, T., Drettakis, G.
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Automobiles Cameras Computer Science Datasets Generative adversarial networks Graphics Lighting Radiance Rendering Synthesis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!