Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training
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 coherent UI overlays on clean footage. Using this engine, we construct Game2World, comprising 96K s...
| Authors | Wenxuan Shen, Dongna Jin, Dongping Chen |
|---|---|
| Primary category | cs.CV |
| Published | 25 August 2026 |
| Last updated at source | 25 August 2026 |
Models and datasets referencing this paper
- shuaishuaicdp/hud-videoDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.