SOURCE-LINKED INTELLIGENCE

Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Video games provide a scalable source of training data for video world models, offering diverse environments, complex interactions, and abundant in-the-wild gameplay videos. However, raw gameplay footage entangles the game world with screen-space interfaces, introducing game-specific biases and irrelevant dynamics that hinder world-model training. To address this problem, we introduce GameUI-Taxonomy and G2WEngine, a full-stack framework that formalizes gameplay UI grounding and removal. G2WEngine automatically extracts reusable UI assets from real gameplay videos and synthesizes temporally co

Read original source ↗ Open in workspace

recordType

paper

region

Global