Papers
arxiv:2611.23140

GameRealm: Grounding Visual Learning in Interactive Games

Published on Nov 17
· Submitted by
Weiguang Zhao
on Nov 18
Authors:
,
,
,
,
,
,
,
,
,
,

Abstract

GameRealm is a large-scale multimodal gameplay dataset with synchronized depth, camera, audio, control, and 3D trajectory annotations that improves visual foundation models for generation and geometric learning.

Visual foundation models are central to physical intelligence, yet their development remains constrained by fragmented training datasets, inconsistent annotation quality, and limited multimodal supervision. To address these challenges, we introduce GameRealm, a large-scale, richly annotated dataset that grounds visual observations in synchronized, game-native supervision. GameRealm encompasses over 120 million RGB frames and 1,000 hours of gameplay footage across all views. Beyond its unprecedented scale, GameRealm provides rich multimodal supervision, including metric depth, camera parameters, synchronized audio, control inputs, and 3D point trajectories. Its diversity further extends to flexible view configurations, spanning single-view, stereo, multi-view, and panoramic recordings. To enable scalable acquisition across diverse game environments, we develop a unified data collection pipeline that combines human-operated interaction with agentic exploration. Extensive experiments across diverse visual learning tasks demonstrate that GameRealm consistently strengthens visual foundation models in both visual generation and geometric learning. These results establish GameRealm as a versatile and valuable data resource, unlocking new opportunities for advancing visual intelligence.

Community

Paper author Paper submitter

Visual foundation models are central to physical intelligence, yet their development remains constrained by fragmented training datasets, inconsistent annotation quality, and limited multimodal supervision. To address these challenges, we introduce GameRealm, a large-scale, richly annotated dataset that grounds visual observations in synchronized, game-native supervision. GameRealm encompasses over 120 million RGB frames and 1,000 hours of gameplay footage across all views. Beyond its unprecedented scale, GameRealm provides rich multimodal supervision, including metric depth, camera parameters, synchronized audio, control inputs, and 3D point trajectories. Its diversity further extends to flexible view configurations, spanning single-view, stereo, multi-view, and panoramic recordings. To enable scalable acquisition across diverse game environments, we develop a unified data collection pipeline that combines human-operated interaction with agentic exploration. Extensive experiments across diverse visual learning tasks demonstrate that GameRealm consistently strengthens visual foundation models in both visual generation and geometric learning. These results establish GameRealm as a versatile and valuable data resource, unlocking new opportunities for advancing visual intelligence.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.23140 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.23140 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.23140 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.