HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions
- URL: http://arxiv.org/abs/2407.15187v1
- Date: Sun, 21 Jul 2024 14:52:51 GMT
- Title: HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions
- Authors: Haiyang Zhou, Xinhua Cheng, Wangbo Yu, Yonghong Tian, Li Yuan,
- Abstract summary: 3D scene generation is in high demand across various domains, including virtual reality, gaming, and the film industry.
We introduce HoloDreamer, a framework that first generates high-definition panorama as a holistic initialization of the full 3D scene.
We then leverage 3D Gaussian Splatting (3D-GS) to quickly reconstruct the 3D scene, thereby facilitating the creation of view-consistent and fully enclosed 3D scenes.
- Score: 31.342899807980654
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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, the creation of 3D scenes using only text prompts has become viable, thereby significantly advancing researches in text-driven 3D scene generation. In order to obtain multiple-view supervision from 2D diffusion models, prevailing methods typically employ the diffusion model to generate an initial local image, followed by iteratively outpainting the local image using diffusion models to gradually generate scenes. Nevertheless, these outpainting-based approaches prone to produce global inconsistent scene generation results without high degree of completeness, restricting their broader applications. To tackle these problems, we introduce HoloDreamer, a framework that first generates high-definition panorama as a holistic initialization of the full 3D scene, then leverage 3D Gaussian Splatting (3D-GS) to quickly reconstruct the 3D scene, 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.
Related papers
- InsTex: Indoor Scenes Stylized Texture Synthesis [81.12010726769768]
High-quality textures are crucial for 3D scenes for augmented/virtual reality (ARVR) applications.
Current methods suffer from lengthy processing times and visual artifacts.
We introduce two-stage architecture designed to generate high-quality textures for 3D scenes.
arXiv Detail & Related papers (2025-01-22T08:37:59Z) - Wonderland: Navigating 3D Scenes from a Single Image [43.99037613068823]
We introduce a large-scale reconstruction model that uses latents from a video diffusion model to predict 3D Gaussian Splattings for the scenes.
We train the 3D reconstruction model to operate on the video latent space with a progressive training strategy, enabling the efficient generation of high-quality, wide-scope, and generic 3D scenes.
arXiv Detail & Related papers (2024-12-16T18:58:17Z) - SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splatting [53.32467009064287]
We propose a text-driven 3D-consistent scene generation model: SceneDreamer360.
Our proposed method leverages a text-driven panoramic image generation model as a prior for 3D scene generation.
Our experiments demonstrate that SceneDreamer360 with its panoramic image generation and 3DGS can produce higher quality, spatially consistent, and visually appealing 3D scenes from any text prompt.
arXiv Detail & Related papers (2024-08-25T02:56:26Z) - 3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation [51.64796781728106]
We propose a generative refinement network to synthesize new contents with higher quality by exploiting the natural image prior to 2D diffusion model and the global 3D information of the current scene.
Our approach supports wide variety of scene generation and arbitrary camera trajectories with improved visual quality and 3D consistency.
arXiv Detail & Related papers (2024-03-14T14:31:22Z) - Denoising Diffusion via Image-Based Rendering [54.20828696348574]
We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes.
First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes.
Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
arXiv Detail & Related papers (2024-02-05T19:00:45Z) - SceneWiz3D: Towards Text-guided 3D Scene Composition [134.71933134180782]
Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets.
We introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text.
arXiv Detail & Related papers (2023-12-13T18:59:30Z) - Guide3D: Create 3D Avatars from Text and Image Guidance [55.71306021041785]
Guide3D is a text-and-image-guided generative model for 3D avatar generation based on diffusion models.
Our framework produces topologically and structurally correct geometry and high-resolution textures.
arXiv Detail & Related papers (2023-08-18T17:55:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.