ComUICoder: Component-based Reusable UI Code Generation for Complex Websites via Semantic Segmentation and Element-wise Feedback

TL;DR

ComUICoder introduces a component-based framework utilizing semantic segmentation and element-wise feedback to enhance UI code generation for complex, multi-page websites, addressing fragmentation and redundancy issues faced by existing models.

Contribution

It presents a novel framework combining semantic-aware segmentation, graph-based component merging, and fine-grained feedback to improve code quality and reusability in complex website UI generation.

Findings

Significant improvement in code quality and consistency.

Enhanced reusability of UI components across pages.

Effective handling of complex, multi-page website structures.

Abstract

Multimodal Large Language Models (MLLMs) have demonstrated strong performance on the UI-to-code task, which aims to generate UI code from design mock-ups. However, when applied to long and complex websites, they often struggle with fragmented segmentation, redundant code generation for repetitive components, and frequent UI inconsistencies. To systematically investigate and address these challenges, we introduce ComUIBench, a new multi-page complex webpage benchmark with component annotations, designed to evaluate MLLMs' ability to generate reusable UI code in realistic website scenarios. Building upon this benchmark, we propose ComUICoder, a component-based UI code generation framework that emphasizes semantic-aware segmentation, code reuse, and fine-grained refinement. Specifically, ComUICoder incorporates (1) Hybrid Semantic-aware Block Segmentation for accurate UI semantic coherent block detection, (2) Visual-aware Graph-based Block Merge to consolidate structurally similar components within and across webpages for reusable implementation, and (3) Priority-based Element-wise Feedback to refine generated code and reduce element-level inconsistencies. Extensive experiments demonstrate that ComUICoder significantly improves overall generation quality and code reusability on complex multipage websites. Our datasets and code are publicly available at https://github.com/WebPAI/ComUICoder.