Neural Radiance Fields (NeRFs) can be dramatically accelerated by spatial grid representations. However, they do not explicitly reason about scale and so introduce aliasing artifacts when reconstructing scenes captured at different camera distances. Mip-NeRF and its extensions propose scale-aware renderers that project volumetric frustums rather than point samples but such approaches rely on positional encodings that are not readily compatible with grid methods. We propose a simple modification to grid-based models by training model heads at different spatial grid resolutions. At render time, we simply use coarser grids to render samples that cover larger volumes. Our method can be easily applied to existing accelerated NeRF methods and significantly improves rendering quality (reducing error rates by 20-90% across synthetic and unbounded real-world scenes) while incurring minimal performance overhead (as each model head is quick to evaluate). Compared to Mip-NeRF, we reduce error rates by 20% while training over 60x faster.

翻译：神经辐射场（NeRFs）可通过空间网格表示实现显著加速，但其未显式考虑尺度因素，因此在重建不同相机距离下捕捉的场景时会产生混叠伪影。Mip-NeRF及其扩展方法提出基于体积截锥体而非点采样的尺度感知渲染器，但此类方法依赖于与网格方法不兼容的位置编码。我们提出一种对网格模型的简单改进，即在不同的空间网格分辨率下训练模型头。在渲染时，我们仅需使用更粗糙的网格来对覆盖更大体积的样本进行渲染。该方法可轻松应用于现有加速NeRF方法，在带来极小性能开销（每个模型头可快速评估）的同时显著提升渲染质量（在合成场景与无界真实场景中错误率降低20%-90%）。与Mip-NeRF相比，我们在训练速度快60倍以上的基础上将错误率降低了20%。