Abstract
The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360$^{\circ}$ scene generation pipeline that facilitates the creation of comprehensive 360$^{\circ}$ scenes for in-the-wild environments in a matter of minutes. Our approach utilizes the generative power of a 2D diffusion model and prompt self-refinement to create a high-quality and globally coherent panoramic image. This image acts as a preliminary "flat" (2D) scene representation. Subsequently, it is lifted into 3D Gaussians, employing splatting techniques to enable real-time exploration. To produce consistent 3D geometry, our pipeline constructs a spatially coherent structure by aligning the 2D monocular depth into a globally optimized point cloud. This point cloud serves as the initial state for the centroids of 3D Gaussians. In order to address invisible issues inherent in single-view inputs, we impose semantic and geometric constraints on both synthesized and input camera views as regularizations. These guide the optimization of Gaussians, aiding in the reconstruction of unseen regions. In summary, our method offers a globally consistent 3D scene within a 360$^{\circ}$ perspective, providing an enhanced immersive experience over existing techniques. Project website at: this http URL
Abstract (translated)
虚拟现实应用程序的需求不断增加,凸显了创建沉浸式的3D资产的重要性。我们提出了一个文本到3D 360$^{\circ}$场景生成管道,用于在几分钟内创建全面的360$^{\circ}$场景。我们的方法利用了2D扩散模型的生成能力以及提示自优化来创建高质量和高全球一致性的全景图像。这个图像作为初步的"平"(2D)场景表示。接着,它被提升到3D高斯分布中,利用插值技术实现实时探索。为了产生一致的3D几何,我们的管道通过将2D单目深度对齐到一个全局优化点云中来构建空间一致的结构。这个点云作为3D高斯圆心的初始状态。为了解决单视图输入中固有的可见问题,我们对合成视图和输入视图施加语义和几何约束作为正则化。这些指导Gaussians的优化,有助于重构未见区域。总之,我们的方法在360$^{\circ}$的视角内提供了一个全球一致的3D场景,提高了现有技术的沉浸体验。项目网站:http:// this http URL
URL
https://arxiv.org/abs/2404.06903