神经辐射场加速算法综述  

A review on neural radiance fields acceleration

作　　者：王稚儒 常远 鲁鹏[3] 潘成伟 WANG Zhiru;CHANG Yuan;LU Peng;PAN Chengwei(Institute of Artificial Intelligence,Beihang University,Beijing 100191,China;China Telecom Research Institute,Beijing 102209,China;School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]北京航空航天大学人工智能研究院,北京100191 [2]中国电信股份有限公司研究院,北京102209 [3]北京邮电大学人工智能学院,北京100876

出　　处：《图学学报》2024年第1期1-13,共13页Journal of Graphics

基　　金：新一代人工智能国家科技重大专项(2022ZD0116401)。

摘　　要：近年来,神经辐射场(NeRF)已成为计算机图形学和计算机视觉领域中一个重要的研究方向,因其高逼真的视觉合成效果,在真实感渲染、虚拟现实、人体建模、城市地图等领域得到了广泛的应用。NeRF利用神经网络从输入图片集中学习三维场景的隐式表征,并合成高逼真的新视角图像。然而原始NeRF模型的训练和推理速度都很慢,难以在真实环境下部署与应用。针对NeRF的加速问题,研究者们从场景建模方法、光线采样策略等方面展开对NeRF进行提速的研究。该类工作大致可分为以下研究方向:烘焙模型、与离散表示方法结合、提高采样效率、利用哈希编码降低MLP网络复杂度、引入场景泛化性、引入深度监督信息和分解方法。通过介绍NeRF模型提出的背景,对上述思路的代表方法的优势与特点进行了讨论和分析,最后总结了NeRF相关工作在加速方面所取得的进展和对于未来的展望。Neural radiance field(NeRF)has become an important research area in computer graphics and computer vision in recent years.Due to its highly realistic visual synthesis effects,NeRF has been widely used in photorealistic rendering,virtual reality,human body modeling,urban mapping,and other domains.NeRF employs neural networks to learn implicit representations of 3D scenes from input image sets and to synthesize highly realistic novel view images.However,the training and inference speeds of the primitive NeRF model are very slow,posing challenges for real-condition deployment and application.To address the acceleration problem of NeRF,researchers have studied the acceleration of NeRF from the aspects of scene modeling methods and ray sampling strategies.Those works can be categorized into the following research directions:baking model,integrating models with discrete representation methods,enhancing sampling efficiency,using hash coding to reduce the complexity of MLP network,introducing scene generalization,and introducing deep supervision information and field decomposition methods.After introducing the background of the NeRF model,the advantages and characteristics of the representative methods of the above ideas were discussed and analyzed.Finally,the progress made in the acceleration of NeRF-related work and future prospects were summarized.

关 键 词：神经辐射场 视点合成 神经渲染 NeRF加速 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]