Interactive Sketch-Based Normal Map Generation with Deep Neural Networks

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings of ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (i3D)
Place of PublicationNew York
PublisherACM 
ISBN (Print)123-4567-24-567/08/06
Publication statusPublished - May 2018

Conference

TitleACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (i3D 2018)
LocationUbisoft Montréal
PlaceCanada
CityMontreal
Period15 - 18 May 2018

Link(s)

Abstract

High-quality normal maps are important intermediates for representing complex shapes. In this paper, we propose an interactive system for generating normal maps with the help of deep learning techniques. Utilizing the Generative Adversarial Network (GAN) framework, our method produces high quality normal maps with sketch inputs. In addition, we further enhance the interactivity of our system by incorporating user-specified normals at selected points. Our method generates high quality normal maps in real time. Through comprehensive experiments, we show the effectiveness and robustness of our method. A thorough user study indicates the normal maps generated by our method achieve a lower perceptual difference from the ground truth compared to the alternative methods.

Research Area(s)

  • Sketch, Normal Map, Point Hints, Generative Adversarial Network, Wasserstein Distance

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

Interactive Sketch-Based Normal Map Generation with Deep Neural Networks. / Su, Wanchao; Du, Dong; Yang, Xin; Zhou, Shizhe; Fu, Hongbo.

Proceedings of ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (i3D). New York : ACM , 2018. 4.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

Download Statistics

No data available