mlsanityData to 7 Oct 2026

Unconditional Scene Graph Generation

arXiv 2108.05884 ↗First posted 12 Aug 2021cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 12 Aug 2021.

Builds on

32 of 45 references.

References · 32

  1. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  2. 2016Improved Techniques for Training GANscited by 2,938
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  4. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  5. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  6. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  7. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  8. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  9. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  10. 2018Assessing Generative Models via Precision and Recallcited by 401
  11. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  12. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
20 more
  1. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  2. 2018Image Generation from Scene Graphscited by 324
  3. 2017Community Detection and Stochastic Block Modelscited by 317
  4. 2018Graph R-CNN for Scene Graph Generationcited by 296
  5. 2015A note on the evaluation of generative modelscited by 291
  6. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 231
  7. 2018Learning Deep Generative Models of Graphscited by 227
  8. 2020Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructionscited by 205
  9. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  10. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 159
  11. 2018NetGAN: Generating Graphs via Random Walkscited by 129
  12. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  13. 2018Graphite: Iterative Generative Modeling of Graphscited by 112
  14. 2020Semantic Image Manipulation Using Scene Graphscited by 82
  15. 2018Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generationcited by 78
  16. 2019Specifying Object Attributes and Relations in Interactive Scene Generationcited by 76
  17. 2017Pixels to Graphs by Associative Embeddingcited by 58
  18. 2019SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentationcited by 55
  19. 2019Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attentioncited by 26
  20. 2019Labeled Graph Generative Adversarial Networkscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 7; 2024: 7; 2025: 1; 2026: 3.

22 papers.

Sort:

By area:

  1. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 110
  2. 2023SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesiscited by 41
  3. 2023Incremental 3D Semantic Scene Graph Prediction from RGB Sequencescited by 39
  4. 2024Segment Anything Model for Road Network Graph Extractioncited by 28
  5. 2021MIGS: Meta Image Generation from Scene Graphscited by 7
  6. 2024InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Priorcited by 6
  7. 2022DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulationcited by 4
  8. 2024Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Modelscited by 4
  9. 2022GEMS: Scene Expansion using Generative Models of Graphscited by 3
  10. 2023Generalized Unbiased Scene Graph Generationcited by 3
  11. 2023PRISM: Progressive Restoration for Scene Graph-based Image Manipulationcited by 3
  12. 2023Instance-incremental Scene Graph Generation from Real-world Point Clouds via Normalizing Flowscited by 2
10 more
  1. 2023LIC-GAN: Language Information Conditioned Graph Generative GAN Modelcited by 2
  2. 2022Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generationcited by 1
  3. 2023Integrating Symbolic Reasoning into Neural Generative Models for Design Generationcited by 1
  4. 2024Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Imagescited by 1
  5. 2025FORESCENE: FOREcasting human activity via latent SCENE graphs diffusioncited by 1
  6. 2024Generated Contents Enrichmentcited by 0
  7. 2024GraphSCENE: On-Demand Critical Scenario Generation for Autonomous Vehicles in Simulationcited by 0
  8. 2026BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detectioncited by 0
  9. 2026Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matchingcited by 0
  10. 2026Dependency-Aware Discrete Diffusion for Scene Graph Generationcited by 0