Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale to large scenes. We present a Memory-Efficient Radiance Field (MERF) representation that achieves real-time rendering of large-scale scenes in a browser. MERF reduces the memory consumption of prior sparse volumetric radiance fields using a combination of a sparse feature grid and high-resolution 2D feature planes. To support large-scale unbounded scenes, we introduce a novel contraction function that maps scene coordinates into a bounded volume while still allowing for efficient ray-box intersection. We design a lossless procedure for baking the parameterization used during training into a model that achieves real-time rendering while still preserving the photorealistic view synthesis quality of a volumetric radiance field.

翻译：神经辐射场实现了最先进的光写实视图合成。然而，现有的辐射场表示要么计算密集度过高，无法实现实时渲染，要么内存占用过多，难以扩展到大规模场景。本文提出一种内存高效辐射场表示，能够在浏览器中实现大规模场景的实时渲染。MERF通过结合稀疏特征网格和高分辨率2D特征平面，降低了先前稀疏体素辐射场的内存消耗。为支持大规模无界场景，我们引入一种新颖的收缩函数，该函数将场景坐标映射到有界体积内，同时仍允许高效的射线-包围盒求交。我们设计了一种无损流程，将训练过程中使用的参数化方法烘焙到模型中，该模型在实现实时渲染的同时，仍能保持体素辐射场的光写实视图合成质量。