Unconditional Scene Graph Generation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionGraph GenerationImage GenerationObjectScene Graph GenerationSimilar Papers 제목 키워드 기반
End-to-End Optimization of Scene Layout
We propose an end-to-end variational generative model for scene layout synthesis conditioned on scene graphs. Unlike unconditional scene layout generation, we use scene graphs as an abstract but general representation to…
DiversityIndoor Scene ReconstructionIndoor Scene SynthesisLayout Generation+2Unconditional Synthesis of Complex Scenes Using a Semantic Bottleneck
Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthe…
Image GenerationSegmentationJoint Generative Modeling of Scene Graphs and Images via Diffusion Models
In this paper, we present a novel generative task: joint scene graph - image generation. While previous works have explored image generation conditioned on scene graphs or layouts, our task is distinctive and important a…
Graph GenerationImage GenerationScene Graph DetectionScene Graph GenerationTowards Improving the Generation Quality of Autoregressive Slot VAEs
Unconditional scene inference and generation are challenging to learn jointly with a single compositional model. Despite encouraging progress on models that extract object-centric representations (''slots'') from images,…
Image GenerationObjectScene GenerationScene Understanding+1Semantic Bottleneck Scene Generation
Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthe…
Conditional Image GenerationImage GenerationImage-to-Image TranslationScene Generation+1