PyNeRF：金字塔形神经辐射场

摘要

神经辐射场（NeRFs）可以通过空间网格表示大幅加速。然而，它们并未明确推理比例尺，因此在重建以不同摄像机距离捕获的场景时会引入混叠伪影。Mip-NeRF及其扩展提出了具有比例感知的渲染器，这些渲染器投影体积视锥而非点采样，但这些方法依赖于位置编码，与网格方法不太兼容。我们提出了一种简单的修改方法，通过在不同空间网格分辨率下训练模型头部。在渲染时，我们简单地使用更粗的网格来渲染覆盖更大体积的样本。我们的方法可以轻松应用于现有的加速NeRF方法，并显著改善渲染质量（在合成和无界真实场景中，将误差率降低了20-90%），同时带来最小的性能开销（因为每个模型头部的评估速度很快）。与Mip-NeRF相比，我们将误差率降低了20%，同时训练速度提高了60倍。

English

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.

PyNeRF：金字塔形神经辐射场

PyNeRF: Pyramidal Neural Radiance Fields

摘要

Support