We present a method for reconstructing high-quality meshes of large unbounded real-world scenes suitable for photorealistic novel view synthesis. We first optimize a hybrid neural volume-surface scene representation designed to have well-behaved level sets that correspond to surfaces in the scene. We then bake this representation into a high-quality triangle mesh, which we equip with a simple and fast view-dependent appearance model based on spherical Gaussians. Finally, we optimize this baked representation to best reproduce the captured viewpoints, resulting in a model that can leverage accelerated polygon rasterization pipelines for real-time view synthesis on commodity hardware. Our approach outperforms previous scene representations for real-time rendering in terms of accuracy, speed, and power consumption, and produces high quality meshes that enable applications such as appearance editing and physical simulation.

翻译：我们提出了一种方法，用于重建适用于逼真新视角合成的大规模无界真实场景的高质量网格。首先，我们优化了一种混合神经体积-表面场景表示，该表示设计为具有与场景表面对应的良好水平集。然后，我们将此表示“烘焙”为高质量三角网格，并为其配备基于球面高斯分布的简单快速视点相关外观模型。最后，我们优化此烘焙表示以最佳地再现捕获的视角，从而得到一个可利用加速多边形光栅化流水线在通用硬件上实现实时视图合成的模型。我们的方法在准确性、速度和功耗方面优于先前的实时渲染场景表示，并生成高质量网格，支持外观编辑和物理模拟等应用。