StructLayoutFormer:Conditional Structured Layout Generation via Structure Serialization and Disentanglement
Authors:
- Xin HuXHXin Hu
- Pengfei XuPXPengfei Xu
- Jin ZhouJZJin Zhou
- Hongbo FuHFHongbo Fu
- Hui HuangHHHui Huang
Preprint
Abstract
Structured layouts are preferable in many 2D visual contents (\eg, GUIs, webpages) since the structural information allows convenient layout editing. Computational frameworks can help create structured layouts but require heavy labor input. Existing data-driven approaches are effective in automatically generating fixed layouts but fail to produce layout structures. We present StructLayoutFormer, a novel Transformer-based approach for conditional structured layout generation. We use a structure serialization scheme to represent structured layouts as sequences. To better control the structures of generated layouts, we disentangle the structural information from the element placements. Our approach is the first data-driven approach that achieves conditional structured layout generation and produces realistic layout structures explicitly. We compare our approach with existing data-driven layout generation approaches by including post-processing for structure extraction. Extensive experiments have shown that our approach exceeds these baselines in conditional structured layout generation. We also demonstrate that our approach is effective in extracting and transferring layout structures. The code is publicly available at %\href{https://github.com/Teagrus/StructLayoutFormer} {https://github.com/Teagrus/StructLayoutFormer}.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- LayoutGPT: Compositional Visual Planning and Generation with Large Language Models2023
- Coarse-to-Fine Generative Modeling for Graphic LayoutsProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Modeling Visual Containment for Web Page Layout OptimizationComputer Graphics Forum, 2021
- Attribute-Conditioned Layout GAN for Automatic Graphic DesignIEEE Transactions on Visualization and Computer Graphics, 2020
- Global Beautification of 2D and 3D Layouts With Interactive Ambiguity ResolutionIEEE Transactions on Visualization and Computer Graphics, 2019
- Content-aware generative modeling of graphic design layoutsACM Transactions on Graphics, 2019
- Learning Layouts for Single-PageGraphic DesignsIEEE Transactions on Visualization and Computer Graphics, 2014