Unconditional Scene Graph Generation
Garg S, Dhamo H, Farshad A, Musatian S, Navab N, Tombari F (2021)
Publication Type: Conference contribution
Publication year: 2021
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 16342-16351
Conference Proceedings Title: Proceedings of the IEEE International Conference on Computer Vision
Event location: Virtual, Online, CAN
ISBN: 9781665428125
DOI: 10.1109/ICCV48922.2021.01605
Abstract
Despite recent advancements in single-domain or single-object image generation, it is still challenging to generate complex scenes containing diverse, multiple objects and their interactions. Scene graphs, composed of nodes as objects and directed-edges as relationships among objects, offer an alternative representation of a scene that is more semantically grounded than images. We hypothesize that a generative model for scene graphs might be able to learn the underlying semantic structure of real-world scenes more effectively than images, and hence, generate realistic novel scenes in the form of scene graphs. In this work, we explore a new task for the unconditional generation of semantic scene graphs. We develop a deep auto-regressive model called SceneGraphGen which can directly learn the probability distribution over labelled and directed graphs using a hierarchical recurrent architecture. The model takes a seed object as input and generates a scene graph in a sequence of steps, each step generating an object node, followed by a sequence of relationship edges connecting to the previous nodes. We show that the scene graphs generated by SceneGraphGen are diverse and follow the semantic patterns of real-world scenes. Additionally, we demonstrate the application of the generated graphs in image synthesis, anomaly detection and scene graph completion.
Involved external institutions
Germany (DE)How to cite
APA:
Garg, S., Dhamo, H., Farshad, A., Musatian, S., Navab, N., & Tombari, F. (2021). Unconditional Scene Graph Generation. In Proceedings of the IEEE International Conference on Computer Vision (pp. 16342-16351). Virtual, Online, CAN: Institute of Electrical and Electronics Engineers Inc..
MLA:
Garg, Sarthak, et al. "Unconditional Scene Graph Generation." Proceedings of the 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021, Virtual, Online, CAN Institute of Electrical and Electronics Engineers Inc., 2021. 16342-16351.
BibTeX: Download