We present NeRF-XL, a principled method for distributing Neural Radiance Fields (NeRFs) across multiple GPUs, thus enabling the training and rendering of NeRFs with an arbitrarily large capacity. We begin by revisiting existing multi-GPU approaches, which decompose large scenes into multiple independently trained NeRFs, and identify several fundamental issues with these methods that hinder improvements in reconstruction quality as additional computational resources (GPUs) are used in training. NeRF-XL remedies these issues and enables the training and rendering of NeRFs with an arbitrary number of parameters by simply using more hardware. At the core of our method lies a novel distributed training and rendering formulation, which is mathematically equivalent to the classic single-GPU case and minimizes communication between GPUs. By unlocking NeRFs with arbitrarily large parameter counts, our approach is the first to reveal multi-GPU scaling laws for NeRFs, showing improvements in reconstruction quality with larger parameter counts and speed improvements with more GPUs. We demonstrate the effectiveness of NeRF-XL on a wide variety of datasets, including the largest open-source dataset to date, MatrixCity, containing 258K images covering a 25km^2 city area.

翻译：我们提出NeRF-XL，一种将神经辐射场（NeRF）分布至多GPU的规范性方法，从而支持任意大规模容量NeRF的训练与渲染。首先，我们回顾现有多GPU方案——这些方法将大场景分解为多个独立训练的NeRF，并指出此类方法存在若干根本性问题，导致在训练中增加计算资源（GPU）时无法提升重建质量。NeRF-XL通过简单增加硬件即可解决这些问题，实现任意参数量的NeRF训练与渲染。该方法的核心是一种新颖的分布式训练与渲染公式，数学上等价于经典单GPU场景，并最小化GPU间通信。通过解锁超大规模参数量的NeRF，本研究首次揭示NeRF的多GPU缩放定律：更大参数量提升重建质量，更多GPU提升速度。我们在多种数据集上验证了NeRF-XL的有效性，包括迄今最大规模开源数据集MatrixCity（覆盖25平方公里城市区域的258K张图像）。