Paper ID: 2411.03709

AutoGameUI: Constructing High-Fidelity Game UIs via Multimodal Learning and Interactive Web-Based Tool

Zhongliang Tang, Mengchen Tan, Fei Xia, Qingrong Cheng, Hao Jiang, Yongxiang Zhang

We introduce an innovative system, AutoGameUI, for efficiently constructing cohesive user interfaces in game development. Our system is the first to address the coherence issue arising from integrating inconsistent UI and UX designs, typically leading to mismatches and inefficiencies. We propose a two-stage multimodal learning pipeline to obtain comprehensive representations of both UI and UX designs, and to establish their correspondences. Through the correspondences, a cohesive user interface is automatically constructed from pairwise designs. To achieve high-fidelity effects, we introduce a universal data protocol for precise design descriptions and cross-platform applications. We also develop an interactive web-based tool for game developers to facilitate the use of our system. We create a game UI dataset from actual game projects and combine it with a public dataset for training and evaluation. Our experimental results demonstrate the effectiveness of our system in maintaining coherence between the constructed interfaces and the original designs.

Submitted: Nov 6, 2024