Unconditional Scene Graph Generation
| Autor: | Sarthak Garg, Helisa Dhamo, Azade Farshad, Sabrina Musatian, Nassir Navab, Federico Tombari |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | 2021 IEEE/CVF International Conference on Computer Vision (ICCV). |
| Popis: | 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. Comment: accepted for publication at ICCV 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|