Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, while allowing the rendering of high-resolution images in real-time. However, leveraging 3D Gaussians for surface reconstruction poses significant challenges due to the explicit and disconnected nature of 3D Gaussians. In this work, we present Gaussian Opacity Fields (GOF), a novel approach for efficient, high-quality, and adaptive surface reconstruction in unbounded scenes. Our GOF is derived from ray-tracing-based volume rendering of 3D Gaussians, enabling direct geometry extraction from 3D Gaussians by identifying its levelset, without resorting to Poisson reconstruction or TSDF fusion as in previous work. We approximate the surface normal of Gaussians as the normal of the ray-Gaussian intersection plane, enabling the application of regularization that significantly enhances geometry. Furthermore, we develop an efficient geometry extraction method utilizing Marching Tetrahedra, where the tetrahedral grids are induced from 3D Gaussians and thus adapt to the scene's complexity. Our evaluations reveal that GOF surpasses existing 3DGS-based methods in surface reconstruction and novel view synthesis. Further, it compares favorably to or even outperforms, neural implicit methods in both quality and speed.

中文翻译：

---

Gaussian Opacity Fields：无界场景中的高效自适应表面重建


最近，3D 高斯展开 （3DGS） 展示了令人印象深刻的新颖视图合成结果，同时允许实时渲染高分辨率图像。然而，由于 3D Gaussian 的显式和断开连接的性质，利用 3D Gaussian 进行表面重建带来了重大挑战。在这项工作中，我们提出了高斯不透明场 （GOF），这是一种在无界场景中进行高效、高质量和自适应表面重建的新方法。我们的 GOF 源自基于光线追踪的 3D 高斯体积渲染，通过识别其水平集，可以从 3D 高斯直接提取几何图形，而无需像以前的工作那样求助于泊松重建或 TSDF 融合。我们将高斯的表面法线近似为射线-高斯交点平面的法线，从而能够应用正则化，从而显著增强几何结构。此外，我们开发了一种利用行进四面体的高效几何提取方法，其中四面体网格是从 3D 高斯诱导的，从而适应场景的复杂性。我们的评估表明，GOF 在表面重建和新颖的视图合成方面超越了现有的基于 3DGS 的方法。此外，它在质量和速度方面都优于神经隐式方法，甚至优于神经隐式方法。