SphericalDreamer: Generating Navigable Immersive 3D Worlds with Panorama Fusion

TL;DR

SphericalDreamer is a novel method that generates detailed, immersive, and navigable 3D outdoor environments from text by fusing multiple panoramic images into a consistent 3D space.

Contribution

It introduces a panoramic image fusion technique that enables long-range, fully immersive 3D environment generation from textual prompts, overcoming previous limitations.

Findings

Produces highly detailed 3D environments from text prompts.

Improves scale and navigability over prior methods.

Maintains visual and geometric consistency in fused panoramas.

Abstract

The generation of immersive and navigable 3D environments is increasingly prevalent with the growing adoption of virtual reality and 3D content. However, recent methods face a fundamental limitation: they cannot produce 3D worlds that simultaneously (i) are navigable over long-range spatial extents and (ii) cover the complete omnidirectional field of view ($360^\circ$ horizontally and $180^\circ$ vertically). To address this challenge, we introduce SphericalDreamer, a method for generating fully immersive and long-range 3D outdoor environments from textual prompts. Our approach is built on the generation of multiple panoramic images, which are subsequently lifted into 3D and fused together while maintaining visual and geometric consistency. SphericalDreamer produces highly detailed, fully immersive 3D environments, while substantially improving scale and navigability compared to prior approaches.