SphericalDreamer: Generating Navigable Immersive 3D Worlds with Panorama Fusion

2026-05-19

AI Summary

Existing methods struggle to simultaneously achieve large-scale navigability and omnidirectional (360° horizontal, 180° vertical) immersive 3D environment generation. This work proposes a novel text-to-3D approach that first synthesizes multiple panoramic images from textual prompts and then constructs geometrically and visually consistent 3D scenes through 3D lifting and multi-view fusion. The method is the first to enable large-scale outdoor 3D scene generation with full omnidirectional coverage, high-fidelity detail, and long-range continuous navigability. It significantly outperforms current state-of-the-art techniques in terms of immersion, spatial scale, visual richness, and navigational coherence.

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.

Problem

• navigable 3D environments
• omnidirectional field of view
• immersive 3D generation
• long-range spatial extent
• panorama fusion

Innovation

• panorama fusion
• navigable 3D generation
• omnidirectional 3D
• text-to-3D
• immersive environment