SPRITE: From Static Mockups to Engine-Ready Game UI
Summary
SPRITE introduces a pipeline that converts static game UI screenshots into editable engine assets using vision-language models and YAML to handle complex layouts and nesting.
View Cached Full Text
Cached at: 04/22/26, 06:17 AM
Paper page - SPRITE: From Static Mockups to Engine-Ready Game UI
Source: https://huggingface.co/papers/2604.18591
Abstract
SPRITE enables automated conversion of game UI screenshots into editable engine assets by combining vision-language models with structured YAML representation to handle complex layouts and nesting.
Game UIimplementation 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 editableengine assets. By integratingVision-Language Models(VLMs) with a structuredYAMLintermediate representation, SPRITE explicitly captures complex container relationships and non-rectangular layouts. We evaluated SPRITE against a curatedGame UIbenchmark 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 betweenartistic designandtechnical implementationin game development. Project page: https://baiyunshu.github.io/sprite.github.io/
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2604\.18591
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2604.18591 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2604.18591 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2604.18591 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
CreativeGame:Toward Mechanic-Aware Creative Game Generation
CreativeGame is a multi-agent system that iteratively generates HTML5 games by explicitly planning, tracking, and evolving game mechanics across versions using programmatic rewards and lineage memory.
@op7418: Oops—now it’s actually playable! With Seedance 2.0, the static GPT Image 2 frames for the ARPG *Jin Ping Mei* have been brought to life, complete with UI interactions and seamless scene transitions.
Seedance 2.0 animates static GPT Image 2 frames into a playable ARPG based on Jin Ping Mei, adding UI and smooth scene transitions.
@zan2434: Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exact…
A prototype streams live pixels from an AI model directly to the screen, bypassing HTML, layout engines, and traditional code.
Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
This paper introduces Sparkle, a new dataset and benchmark for instruction-guided video background replacement, addressing the lack of high-quality training data in this domain. It proposes a scalable pipeline with decoupled guidance to generate realistic foreground-background interactions.
playcanvas/supersplat
SuperSplat is a free, open-source browser-based editor for inspecting, editing, optimizing, and publishing 3D Gaussian Splats, built on web technologies by PlayCanvas. It requires no installation and is available live at superspl.at/editor.