Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

ArchGANs: Stylized Colorization Prototyping for Architectural Line Drawing

: Tao, Wenyuan; Jiang, Han; Sun, Qian; Zhang, Mu; Chen, Kan; Erdt, Marius


Sourin, Alexei (Ed.) ; Institute of Electrical and Electronics Engineers -IEEE-; European Association for Computer Graphics -EUROGRAPHICS-:
International Conference on Cyberworlds, CW 2020. Proceedings : 29 September - 1 October 2020, Caen, France, online
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2020
ISBN: 978-1-7281-6497-7
ISBN: 978-1-7281-6498-4
International Conference on Cyberworlds (CW) <19, 2020, Online>
National Natural Science Foundation of China NSFC
National Natural Science Foundation of China NSFC
Conference Paper
Fraunhofer Singapore ()
Lead Topic: Digitized Work; Research Line: Computer graphics (CG); Research Line: Machine Learning (ML); Generative Adversarial Networks (GAN); Coloring; architectural visualization

Architectural illustration using line drawing with colorization is an important tool and art format. In this paper, in order to generate a natural-looking and high quality water colorlike colorization for architectural line drawing, we propose a novel Generative Adversarial Network (GAN) approach, namely ArchGANs. The proposed ArchGANs unifies a line-feature-aware stylized colorization network (ArchColGAN), which can learn, predict and generate the coloring based on a dataset, as well as a shading generation network (ArchShdGAN), which augments the illustration with controllable lighting effects for better depicting building in 3D. Specifically, ArchColGAN can preserve the essential line features and building part correlation property, it also tackles the uneven colorization problem caused by the sparse lines. Experimental results demonstrate our proposed method is effective and suitable for colorization prototyping.