InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation
The paper introduces InfiniDream, a VLM-driven framework for open-ended procedural 3D world generation.
InfiniDream introduces a novel framework that combines symbolic asset generation and text-to-world pipelines to create complex, photorealistic 3D worlds, addressing the limitations of existing VLM-guided procedural methods.
Before reading this…
Applications
- →video games
- →virtual reality
To understand this paper, make sure you know these concepts first:
- procedural generationfind papers →
Abstract
More Like ThisProcedural generation plays a key role in synthetic data creation and game development, offering greater controllability, editability, and diversity than static mesh representations. However, VLM-based code generation often produces relatively simple 3D assets, while sophisticated photorealistic procedural systems require extensive manual development. Existing VLM-guided procedural methods remain largely constrained by predefined factories and APIs, limiting their ability to create novel asset types. We introduce InfiniDream, a VLM-driven framework for open-ended procedural 3D world generation. First, we propose Symbolically Constrained Asset Generation, which leverages existing procedural algorithms to create novel, photorealistic assets while preserving editability and seed-based diversity. Second, we develop an end-to-end text-to-world pipeline that combines semantic scene planning with Deterministic Frustum-Guided Grid Placement to construct large-scale 3D worlds with precise object placement, procedural population, and animation. Extensive evaluations on 100 object and 20 scene generation tasks demonstrate improvements across four perceptual metrics. Diversity analysis, ablation studies, and human preference evaluations further validate the effectiveness of our framework. Project page: https://yichuanh.github.io/infinidream-page/