NeRF-XL: Scaling NeRFs with Multiple GPUs

arXiv:2404.16221v1 Announce Type: new
Abstract: 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 …

abstract arxiv capacity cs.cv cs.dc cs.gr enabling fields fundamental gpu gpus identify multi-gpu multiple nerf neural radiance fields rendering scaling training type