Generative Layout Modeling Using Constraint Graphs

Wamiq Para, Paul Guerrero, Tom Kelly, Leonidas J. Guibas, Peter Wonka

ICCV 2021 pp. 6690-6700

doi:10.1109/ICCV48922.2021.00662 /iccv/2021/para2021iccv-generative/

Abstract

We propose a new generative model for layout generation. We generate layouts in three steps. First, we generate the layout elements as nodes in a layout graph. Second, we compute constraints between layout elements as edges in the layout graph. Third, we solve for the final layout using constrained optimization. For the first two steps, we build on recent transformer architectures. The layout optimization implements the constraints efficiently. We show three practical contributions compared to the state of the art: our work requires no user input, produces higher quality layouts, and enables many novel capabilities for conditional layout generation.

PDF ICCV Semantic Scholar

Cite

Text

Para et al. "Generative Layout Modeling Using Constraint Graphs." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00662

Markdown

[Para et al. "Generative Layout Modeling Using Constraint Graphs." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/para2021iccv-generative/) doi:10.1109/ICCV48922.2021.00662

BibTeX

@inproceedings{para2021iccv-generative,
  title     = {{Generative Layout Modeling Using Constraint Graphs}},
  author    = {Para, Wamiq and Guerrero, Paul and Kelly, Tom and Guibas, Leonidas J. and Wonka, Peter},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {6690-6700},
  doi       = {10.1109/ICCV48922.2021.00662},
  url       = {https://mlanthology.org/iccv/2021/para2021iccv-generative/}
}