NerfAcc：高效取樣加速 NeRFs

NerfAcc: Efficient Sampling Accelerates NeRFs

May 8, 2023

作者: Ruilong Li, Hang Gao, Matthew Tancik, Angjoo Kanazawa

cs.AI

摘要

由於體積渲染所需的樣本數眾多，優化和渲染神經輻射場具有高度的計算成本。最近的研究已包括替代取樣方法，以加速其方法，然而，這些方法通常不是工作的重點。在本文中，我們研究並比較多種取樣方法，並展示改進的取樣通常適用於統一的透射率估算器概念下的各種 NeRF 變體。為了促進未來的實驗，我們開發了 NerfAcc，一個 Python 工具箱，提供靈活的 API，以將先進的取樣方法納入與 NeRF 相關的方法中。我們通過展示其靈活性，顯示它可以將幾種最近的 NeRF 方法的訓練時間減少 1.5 到 20 倍，並對現有代碼庫進行最小修改。此外，高度定制的 NeRF，如 Instant-NGP，可以使用 NerfAcc 在本機 PyTorch 中實現。

English

Optimizing and rendering Neural Radiance Fields is computationally expensive due to the vast number of samples required by volume rendering. Recent works have included alternative sampling approaches to help accelerate their methods, however, they are often not the focus of the work. In this paper, we investigate and compare multiple sampling approaches and demonstrate that improved sampling is generally applicable across NeRF variants under an unified concept of transmittance estimator. To facilitate future experiments, we develop NerfAcc, a Python toolbox that provides flexible APIs for incorporating advanced sampling methods into NeRF related methods. We demonstrate its flexibility by showing that it can reduce the training time of several recent NeRF methods by 1.5x to 20x with minimal modifications to the existing codebase. Additionally, highly customized NeRFs, such as Instant-NGP, can be implemented in native PyTorch using NerfAcc.