arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.10474cs.DC
收藏

面向分布式智能的联邦神经辐射场

Federated Neural Radiance Field for Distributed Intelligence

Yintian Zhang, Ziyu Shao

AI总结:

针对分布式数据存储下NeRF训练图像受法规与隐私限制的问题,本文构建联邦学习测试平台并部署FedNeRF,在部分客户端选择下验证其隐私保护式协同训练的可行性。

摘要:

新视角合成(NVS)是许多AR和VR应用中的一项重要技术。近期提出的Neural Radiance Field(NeRF,神经辐射场)方法已在NVS任务上展现出卓越性能,并已应用于其他相关领域。然而,由于严格的法规和隐私问题,某些具有分布式数据存储特点的应用场景可能会给NeRF方法获取训练图像带来挑战。为克服这一挑战,我们聚焦于FedNeRF,这是一种基于联邦学习(FL)的NeRF方法,可在保护数据隐私的同时利用不同数据所有者处可用的图像。在本文中,我们首先构建了一个资源丰富、功能多样的联邦学习测试平台。随后,我们在这一实际FL系统中部署FedNeRF算法,并在部分客户端选择的设置下开展FedNeRF实验。预期本文所呈现的关于FedNeRF方法的研究,将有助于推动NeRF方法在分布式数据存储场景中的未来应用。

英文摘要:

Novel view synthesis (NVS) is an important technology for many AR and VR applications. The recently proposed Neural Radiance Field (NeRF) approach has demonstrated superior performance on NVS tasks, and has been applied to other related fields. However, certain application scenarios with distributed data storage may pose challenges on acquiring training images for the NeRF approach, due to strict regulations and privacy concerns. In order to overcome this challenge, we focus on FedNeRF, a federated learning (FL) based NeRF approach that utilizes images available at different data owners while preserving data privacy. In this paper, we first construct a resource-rich and functionally diverse federated learning testbed. Then, we deploy FedNeRF algorithm in such a practical FL system, and conduct FedNeRF experiments with partial client selection. It is expected that the studies of the FedNeRF approach presented in this paper will be helpful to facilitate future applications of NeRF approach in distributed data storage scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑