Valerant builds 3D game maps automatically from single images
Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration
Artificial Intelligence
Summary
Making 3D maps for video games usually requires a lot of manual work. The authors introduce Valerant, a system that can create these maps automatically by exploring virtual worlds using a model that predicts future game states based on actions. Valerant starts from just one image and uses both visual predictions and spatial mapping techniques to build a persistent 3D game map. This approach helps reduce the manual effort needed to design game environments.
What this means in practice
- •For game developers: Automatically generate navigable 3D maps from limited visual input to reduce manual map creation work.
- •For robotics engineers: Use visual-based world models combined with spatial mapping to explore and build 3D environments without physical sensors.
Authors
Yiran Qiao, Feng Wang, Jing Ma
Abstract
World Action Models (WAMs) couple predictive world modeling with action generation, allowing anticipated future states to guide agent behavior. Although WAMs are rapidly advancing embodied AI, general-purpose counterparts remain largely unexplored in games. Existing game-oriented approaches often combine action-conditioned world models with external policies and reward functions to realize WAM-like decision-making, yet they operate mainly in 2D visual observation space and do not instantiate persistent 3D geometry. Extending this paradigm to 3D games introduces a distinct challenge. In autonomous driving and robotics, the physical environment exists independently of the model, providing a persistent 3D world in which selected actions can be executed. Games have no such external substrate; the virtual world itself must be instantiated. Most playable games require a persistent and navigable space, while 3D games additionally require explicit geometry that supports movement and interaction. Action-conditioned video rollouts provide visual observations but not this spatial representation. We present \textsc{Valerant}, a training-free framework that transforms a pretrained action-conditioned world model into a WAM for exploring and constructing 3D game maps. By coupling predictive visual rollouts with SLAM-based spatial reconstruction and exploration-driven action selection, \textsc{Valerant} progressively transforms a single image into a persistent 3D game map. This framework extends WAM-based interaction beyond 2D visual simulation and offers a new approach to reducing manual effort in 3D game-map creation.