SPRITE: From Static Mockups to Engine-Ready Game UI

TL;DR

SPRITE is a pipeline that converts static game UI mockups into editable engine assets using vision-language models and a structured intermediate representation, improving development efficiency.

Contribution

It introduces a novel approach combining VLMs and YAML to handle complex UI geometries and hierarchies, bridging the gap in existing screenshot-to-code tools.

Findings

SPRITE achieves high fidelity in UI reconstruction.

It reduces manual coding effort in game UI development.

Expert reviews confirm improved prototyping speed.

Abstract

Game UI implementation requires translating stylized mockups into interactive engine entities. However, current "Screenshot-to-Code" tools often struggle with the irregular geometries and deep visual hierarchies typical of game interfaces. To bridge this gap, we introduce SPRITE, a pipeline that transforms static screenshots into editable engine assets. By integrating Vision-Language Models (VLMs) with a structured YAML intermediate representation, SPRITE explicitly captures complex container relationships and non-rectangular layouts. We evaluated SPRITE against a curated Game UI benchmark and conducted expert reviews with professional developers to assess reconstruction fidelity and prototyping efficiency. Our findings demonstrate that SPRITE streamlines development by automating tedious coding and resolving complex nesting. By facilitating rapid in-engine iteration, SPRITE effectively blurs the boundaries between artistic design and technical implementation in game development. Project page: https://baiyunshu.github.io/sprite.github.io/