HoloDreamer: Holistic 3D Panoramic Scene Generation From Text Descriptions
- 25 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (3) , 2541-2554
Abstract
3D scene generation is in high demand across various domains, including virtual reality, gaming, and the film industry. Owing to the powerful generative capabilities of text-to-image diffusion models that provide reliable priors, creating 3D scenes using only text prompts has become viable, thereby significantly advancing research in text-driven 3D scene generation. Prevailing methods typically employ the diffusion model to generate an initial local image, followed by iteratively outpainting the local image to gradually generate scenes. Nevertheless, these outpainting-based approaches are prone to producing globally inconsistent results with low completeness, restricting their broader applications. To tackle these problems, we introduce HoloDreamer, a framework that begins by generating a high-definition panorama to holistically initialize the full scene, and leverages 3D Gaussian Splatting (3D-GS) for rapid 3D scene reconstruction, thereby facilitating the creation of view-consistent and fully enclosed 3D scenes. Specifically, we propose Stylized Equirectangular Panorama Generation, a pipeline that combines multiple diffusion models to enable stylized and detailed equirectangular panorama generation from complex text prompts. Subsequently, Enhanced Two-Stage Panorama Reconstruction is introduced, conducting a two-stage optimization of 3D-GS to inpaint the missing region and enhance the integrity of the scene. Comprehensive experiments demonstrated that our method outperforms prior works in terms of overall visual consistency and harmony, as well as reconstruction quality and rendering robustness when generating fully enclosed scenes.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62202014)
- National Natural Science Foundation of China (62332002)
- National Natural Science Foundation of China (62425101)
This publication has 33 references indexed in Scilit:
- RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion2025
- HiFi-123: Towards High-Fidelity One Image to 3D Content Generation2024
- DreamScene: 3D Gaussian-Based Text-to-3D Scene Generation via Formation Pattern Sampling2024
- DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting2024
- LGM: Large Multi-view Gaussian Model for High-Resolution 3D Content Creation2024
- pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis2021
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019
- Occupancy Networks: Learning 3D Reconstruction in Function Space2019
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018