DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling

Haoran Li, Haolin Shi, Wenli Zhang, Wenjun Wu, Yong Liao*, Lin Wang, Lik-Hang Lee, Peng Yuan Zhou* ;

"Text-to-3D scene generation holds immense potential for the gaming, film, and architecture sectors. Despite significant progress, existing methods struggle with maintaining high quality, consistency, and editing flexibility. In this paper, we propose , a 3D Gaussian-based novel text-to-3D scene generation framework, to tackle the aforementioned three challenges mainly via two strategies. First, employs Formation Pattern Sampling (FPS), a multi-timestep sampling strategy guided by the formation patterns of 3D objects, to form fast, semantically rich, and high-quality representations. FPS uses 3D Gaussian filtering for optimization stability, and leverages reconstruction techniques to generate plausible textures. Second, employs a progressive three-stage camera sampling strategy, specifically designed for both indoor and outdoor settings, to effectively ensure object and environment integration and scene-wide 3D consistency. Last, enhances scene editing flexibility by integrating objects and environments, enabling targeted adjustments. Extensive experiments validate ’s superiority over current state-of-the-art techniques, heralding its wide-ranging potential for diverse applications. Code and demos are released at https://dreamscene-project.github.io."