UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale

arXiv:2511.18005v2 Announce Type: replace Abstract: The automated generation of high-fidelity, city-scale 3D environments remains a formidable challenge with profound academic and industrial implications. However, existing methods struggle to achieve the necessary quality, fidelity, and scalability. To address this, we propose extsc{UrbanWorld2.0}, a reality-aligned intelligent multimodal synthesis engine that creates detailed, city-scale 3D worlds of high fidelity. We introduce an agentic framework that leverages diverse multimodal foundation tools to acquire real-world knowledge, maintain robust intermediate representations, and construct complex 3D scenes.This agentic design, featuring dynamic data processing, iterative self-reflection and refinement, and the invocation of advanced multimodal tools, minimizes cumulative errors and enhances overall performance. Extensive quantitative experiments and qualitative analyzes validate the superior performance of extsc{UrbanWorld2.0} in real-world alignment, shape precision, texture fidelity, and aesthetics level, achieving a win rate of over 86% against existing baselines for overall perceptual quality. This combination of 3D quality, reality alignment, scalability, and seamless compatibility with computer graphics pipelines makes extsc{UrbanWorld2.0} a promising foundation for applications in immersive media, embodied intelligence, and world models.

Source: arXiv cs.CV | 2026-08-18