Corpus ID: 221857360

Scene Graph to Image Generation with Contextualized Object Layout Refinement

@article{Ivgi2020SceneGT,
  title={Scene Graph to Image Generation with Contextualized Object Layout Refinement},
  author={Maor Ivgi and Yaniv Benny and Avichai Ben-David and Jonathan Berant and L. Wolf},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.10939}
}
  • Maor Ivgi, Yaniv Benny, +2 authors L. Wolf
  • Published 2020
  • Computer Science
  • ArXiv
  • Generating high-quality images from scene graphs, that is, graphs that describe multiple entities in complex relations, is a challenging task that attracted substantial interest recently. Prior work trained such models by using supervised learning, where the goal is to produce the exact target image layout for each scene graph. It relied on predicting object locations and shapes independently and in parallel. However, scene graphs are underspecified, and thus the same scene graph often occurs… CONTINUE READING

    Figures and Tables from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES
    Microsoft COCO: Common Objects in Context
    • 10,214
    • Highly Influential
    • Open Access
    Image-to-Image Translation with Conditional Adversarial Networks
    • 6,236
    • Open Access
    Improved Techniques for Training GANs
    • 3,558
    • Open Access
    StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
    • 1,205
    • Open Access
    Conditional Image Synthesis with Auxiliary Classifier GANs
    • 1,329
    • Open Access
    GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
    • 1,725
    • Open Access
    Photographic Image Synthesis with Cascaded Refinement Networks
    • 468
    • Highly Influential
    • Open Access
    Image Generation from Scene Graphs
    • 234
    • Highly Influential
    • Open Access
    Image retrieval using scene graphs
    • 416
    • Highly Influential
    • Open Access