mlsanityData to 14 Oct 2026

Learning Canonical Representations for Scene Graph to Image Generation

arXiv 1912.07414 ↗First posted 16 Dec 2019cs.CVcited by 60

Not on the map. Why?

Abstract (arXiv)

Generating realistic images of complex visual scenes becomes challenging when one wishes to control the structure of the generated images. Previous approaches showed that scenes with few entities can be controlled using scene graphs, but this approach struggles as the complexity of the graph (the number of objects and edges) increases. In this work, we show that one limitation of current methods is their inability to capture semantic equivalence in graphs. We present a novel model that addresses these issues by learning canonical graph representations from the data, resulting in improved image generation for complex visual scenes. Our model demonstrates improved empirical performance on large scene graphs, robustness to noise in the input scene graph, and generalization on semantically equivalent graphs. Finally, we show improved performance of the model on three different benchmarks: Visual Genome, COCO, and CLEVR.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 18; 2024: 11; 2025: 5; 2026: 3.

60 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2023LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Modelscited by 243
  3. 2023Compositional Chain-of-Thought Prompting for Large Multimodal Modelscited by 164
  4. 2021Illiterate DALL-E Learns to Composecited by 147
  5. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  6. 2021Energy-Based Learning for Scene Graph Generationcited by 104
  7. 2024LLARVA: Vision-Action Instruction Tuning Enhances Robot Learningcited by 87
  8. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  9. 2021Object-Region Video Transformerscited by 73
  10. 2021Learning to Compose Visual Relationscited by 72
  11. 2023Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Modelscited by 72
  12. 2022Teaching Structured Vision&Language Concepts to Vision&Language Modelscited by 71
38 more
  1. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 67
  2. 2022Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Trainingcited by 56
  3. 2021Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networkscited by 52
  4. 2023Action Scene Graphs for Long-Form Understanding of Egocentric Videoscited by 51
  5. 2022Modeling Image Composition for Complex Scene Generationcited by 43
  6. 2023SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesiscited by 41
  7. 2023Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphscited by 39
  8. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  9. 2024TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answeringcited by 25
  10. 2022Is an Object-Centric Video Representation Beneficial for Transfer?cited by 24
  11. 2022PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Datacited by 14
  12. 2021AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Stylecited by 11
  13. 2022Scene Graph Expansion for Semantics-Guided Image Outpaintingcited by 11
  14. 2024Scene Graph Disentanglement and Composition for Generalizable Complex Image Generationcited by 11
  15. 2023Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decorationcited by 9
  16. 2022SSGVS: Semantic Scene Graph-to-Video Synthesiscited by 8
  17. 2023Transformer-based Image Generation from Scene Graphscited by 8
  18. 2023Multi-View Graph Representation Learning Beyond Homophilycited by 8
  19. 2021MIGS: Meta Image Generation from Scene Graphscited by 7
  20. 20233VL: Using Trees to Improve Vision-Language Models' Interpretabilitycited by 7
  21. 2025VSC: Visual Search Compositional Text-to-Image Diffusion Modelcited by 7
  22. 2024ReGround: Improving Textual and Spatial Grounding at No Costcited by 6
  23. 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generationcited by 6
  24. 2023Controllable Image Generation via Collage Representationscited by 5
  25. 2024WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentationcited by 4
  26. 2023SPAN: Learning Similarity between Scene Graphs and Images with Transformerscited by 3
  27. 2023PRISM: Progressive Restoration for Scene Graph-based Image Manipulationcited by 3
  28. 2025Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Imagecited by 3
  29. 2026Toward Autonomous Laboratory Safety Monitoring with Vision Language Models: Learning to See Hazards Through Scene Structurecited by 3
  30. 2023GUILGET: GUI Layout GEneration with Transformercited by 2
  31. 2023Multi-object Video Generation from Single Frame Layoutscited by 2
  32. 2023Language-free Compositional Action Generation via Decoupling Refinementcited by 2
  33. 2023Generating by Understanding: Neural Visual Generation with Logical Symbol Groundingscited by 2
  34. 2024Image Synthesis with Graph Conditioning: CLIP-Guided Diffusion Models for Scene Graphscited by 2
  35. 2024Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospectscited by 2
  36. 2025D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognitioncited by 2
  37. 2025Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Modelscited by 2
  38. 2022Transforming Image Generation from Scene Graphscited by 1

50 most cited of 60 All 60 (JSON)