StructLayoutFormer:Conditional Structured Layout Generation via Structure Serialization and Disentanglement

2025-10-30

AI Summary

Existing data-driven layout generation methods produce only fixed pixel-level outputs, making it difficult to explicitly model editable, hierarchical structures—thus limiting controllable generation of 2D content such as GUIs and web pages. To address this, we propose the first conditional structured layout generation framework. Our approach introduces (i) structural serialization—encoding tree-structured layouts into ordered sequences—and (ii) a structure-element decoupling mechanism that separates topological structure from geometric positioning, enabling end-to-end structure-aware generation. Built upon the Transformer architecture, our model supports layout structure extraction, interactive editing, and cross-layout structural transfer. Evaluated on multiple benchmarks, it significantly outperforms state-of-the-art methods, achieving a 12.6% improvement in structural accuracy. Extensive experiments validate the realism, editability, and generalizability of the generated layouts.

Technology Category

• Machine Learning: Structured Learning
• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

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}.

Problem

• Generates structured layouts automatically using Transformer architecture
• Disentangles structural information from element placement for control
• Achieves conditional layout generation with explicit realistic structures

Innovation

• Transformer-based conditional structured layout generation
• Structure serialization scheme for layout sequences
• Disentanglement of structural information from element placements