Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation

Abstract

This paper proposes an image-vector dual diffusion model for generative layout design. Distinct from prior efforts that mostly ignore element-level visual information our approach integrates the power of a pre-trained large image diffusion model to guide layout composition in a vector diffusion model by providing enhanced salient region understanding and high-level inter-element relationship reasoning. Our proposed model simultaneously operates in two domains: it generates the overall design appearance in the image domain while optimizing the size and position of each design element in the vector domain. The proposed method achieves the state-of-the-art results on several datasets and enables new layout design applications.

Cite

Text

Shabani et al. "Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.00881

Markdown

[Shabani et al. "Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/shabani2024cvpr-visual/) doi:10.1109/CVPR52733.2024.00881

BibTeX

@inproceedings{shabani2024cvpr-visual,
  title     = {{Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation}},
  author    = {Shabani, Mohammad Amin and Wang, Zhaowen and Liu, Difan and Zhao, Nanxuan and Yang, Jimei and Furukawa, Yasutaka},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2024},
  pages     = {9222-9231},
  doi       = {10.1109/CVPR52733.2024.00881},
  url       = {https://mlanthology.org/cvpr/2024/shabani2024cvpr-visual/}
}