Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs
Savkin A, Ellouze R, Navab N, Tombari F (2021)
Publication Type: Conference contribution
Publication year: 2021
Journal
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 1229-1235
Conference Proceedings Title: IEEE International Conference on Intelligent Robots and Systems
Event location: Prague, CZE
ISBN: 9781665417143
DOI: 10.1109/IROS51168.2021.9636318
Abstract
Image synthesis driven by computer graphics achieved recently a remarkable realism, yet synthetic image data generated this way reveals a significant domain gap with respect to real-world data. This is especially true in autonomous driving scenarios, which represent a critical aspect for over-coming utilizing synthetic data for training neural networks. We propose a method based on domain-invariant scene representation to directly synthesize traffic scene imagery without rendering. Specifically, we rely on synthetic scene graphs as our internal representation and introduce an unsupervised neural network architecture for realistic traffic scene synthesis. We enhance synthetic scene graphs with spatial information about the scene and demonstrate the effectiveness of our approach through scene manipulation.
Involved external institutions
Germany (DE)How to cite
APA:
Savkin, A., Ellouze, R., Navab, N., & Tombari, F. (2021). Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs. In IEEE International Conference on Intelligent Robots and Systems (pp. 1229-1235). Prague, CZE: Institute of Electrical and Electronics Engineers Inc..
MLA:
Savkin, Artem, et al. "Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs." Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021, Prague, CZE Institute of Electrical and Electronics Engineers Inc., 2021. 1229-1235.
BibTeX: Download