SPRITE: From Static Mockups to Engine-Ready Game UI
Not on the map. Why?
Abstract (arXiv)
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/
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 18 Mar 2026.
Builds on
19 of 39 references.
References · 19
- 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
- 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
- 2023StarCoder: may the source be with you!cited by 790
- 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
- 2024Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineeringcited by 146
- 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 141
- 2024Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Datasetcited by 126
- 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 122
- 2017pix2code: Generating Code from a Graphical User Interface Screenshotcited by 113
- 2020Deep Learning for Source Code Modeling and Generation: Models, Applications and Challengescited by 55
- 2019READ: Recursive Autoencoders for Document Layout Generationcited by 51
- 2021VINS: Visual Search for Mobile User Interface Designcited by 37
7 more
- 2024Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approachcited by 24
- 2020LayoutGMN: Neural Graph Matching for Structural Layout Similaritycited by 19
- 2025MLLM-Based UI2Code Automation Guided by UI Layout Informationcited by 17
- 2025Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentationcited by 12
- 2024Misty: UI Prototyping Through Interactive Conceptual Blendingcited by 9
- 2025Widget2Code: From Visual Widgets to UI Code via Multimodal LLMscited by 8
- 2021Erratum: Leveraging Flexible Tree Matching to Repair Broken Locators in Web Automation Scriptscited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation
- 2026Code2Games: Enabling Coding Agents for Gaming World Generation
- 2026GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
- 2026Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training
- 2026GameDevBench: Evaluating Agentic Capabilities Through Game Development
- 2025Automated Unity Game Template Generation from GDDs via NLP and Multi-Modal LLMs
- 2026AutoUE: Automated Generation of 3D Games in Unreal Engine via Multi-Agent Systems
- 2026OpenGame: Open Agentic Coding for Games