Efficient Cloud Pipelines for Neural Radiance Fields
This work addresses the computational bottleneck for deploying NeRFs in real-world applications, but it is incremental as it focuses on optimizing existing cloud infrastructure.
The paper tackles the high computational cost of Neural Radiance Fields (NeRFs) by developing and comparing cloud pipelines on a high-performance academic cluster and Microsoft Azure, enabling their use in client applications like XR and virtual production.
Since their introduction in 2020, Neural Radiance Fields (NeRFs) have taken the computer vision community by storm. They provide a multi-view representation of a scene or object that is ideal for eXtended Reality (XR) applications and for creative endeavors such as virtual production, as well as change detection operations in geospatial analytics. The computational cost of these generative AI models is quite high, however, and the construction of cloud pipelines to generate NeRFs is neccesary to realize their potential in client applications. In this paper, we present pipelines on a high performance academic computing cluster and compare it with a pipeline implemented on Microsoft Azure. Along the way, we describe some uses of NeRFs in enabling novel user interaction scenarios.