Multimodal graph representation learning for website generation based on visual sketch
Preprint
Abstract
The Design2Code problem, which involves converting digital designs into functional source code, is a significant challenge in software development due to its complexity and time-consuming nature. Traditional approaches often struggle with accurately interpreting the intricate visual details and structural relationships inherent in webpage designs, leading to limitations in automation and efficiency. In this paper, we propose a novel method that leverages multimodal graph representation learning to address these challenges. By integrating both visual and structural information from design sketches, our approach enhances the accuracy and efficiency of code generation, particularly in producing semantically correct and structurally sound HTML code. We present a comprehensive evaluation of our method, demonstrating significant improvements in both accuracy and efficiency compared to existing techniques. Extensive evaluation demonstrates significant improvements of multimodal graph learning over existing techniques, highlighting the potential of our method to revolutionize design-to-code automation. Code available at https://github.com/HySonLab/Design2CodeKeywords
All Related Versions
This publication has 13 references indexed in Scilit:
- DeclarUI: Bridging Design and Development with Automated Declarative UI Code GenerationProceedings of the ACM on Software Engineering, 2025
- Graph4GUI: Graph Neural Networks for Representing Graphical User Interfaces2024
- A novel code generator for graphical user interfacesScientific Reports, 2023
- WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics2023
- Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks2023
- Large Language Models Meet NL2Code: A Survey2023
- Gated Graph Recurrent Neural NetworksIEEE Transactions on Signal Processing, 2020
- UNITER: UNiversal Image-TExt Representation Learning2020
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers2019
- pix2code2018