基于NeRF的SLAM研究综述  

Review of NeRF-based SLAM Research

作　　者：喻伟东 鲁静 程晗蕾 YU Wei-Dong;LU Jing;CHENG Han-Lei(Blockchain and Metaverse Laboratory,YGSOFT Inc.,Zhuhai 519085,China;Faculty of Innovation Engineering,Macao University of Science and Technology,Macao 999078,China)

机构地区：[1]远光软件股份有限公司区块链及元宇宙实验室,珠海519085 [2]澳门科技大学创新工程学院,中国澳门999078

出　　处：《计算机系统应用》2025年第4期18-33,共16页Computer Systems & Applications

摘　　要：随着神经辐射场(NeRF)的提出,其基于神经隐式表示场景的方法在生成高保真地图方面具有显著优势,将NeRF应用于同时定位与地图构建(SLAM)中,即基于NeRF的SLAM方法,能够在实现高精度的定位的同时进行连续的3D建模,通过渲染新视角并预测未知区域,提高场景重建的质量和细节.为了跟踪该领域的最新研究成果,对近年来基于NeRF的SLAM的关键算法进行了回顾和综述.首先介绍了NeRF技术的核心原理并全面概述了基于NeRF的SLAM方法的框架,其次重点探讨了基于NeRF的SLAM的改进和优化,包括提高神经隐式表征效率、解决大尺度场景建图问题、增加回环和全局优化实现全局一致性和解决动态干扰问题,最后对基于NeRF的SLAM方法进行了展望,为相关研究人员提供有价值的参考,以促进更多创新研究.The neural radiation field(NeRF)has significant advantages in generating high-fidelity maps thanks to its neural implicit representation-based scene.The application of NeRF in simultaneous localization and mapping(SLAM),namely the NeRF-based SLAM method,enables continuous 3D modeling while achieving high-precision localization to enhance the quality and detail of the scene reconstruction by rendering new perspectives and predicting unknown regions.To track the latest research results in this field,this study reviews and summarizes the key algorithms of NeRF-based SLAM in recent years.Firstly,the core principle of NeRF technology is introduced and a comprehensive overview of the framework of NeRF-based SLAM methods is given,followed by focusing on the improvements and optimizations of NeRF-based SLAM,including improving the efficiency of neural implicit representation,solving the large-scale scene building problem,adding loopback and global optimization to achieve global consistency and solving the dynamic interference problem.Finally,an outlook on the NeRF-based SLAM method is presented to provide valuable references for related researchers to promote more innovative research.

关 键 词：同时定位与地图构建 神经辐射场 神经隐式表示 三维重建 移动机器人 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]