基于3D高斯溅射的3维重建技术综述  

Survey of 3D Reconstruction Techniques Based on 3D Gaussian Splatting

作　　者：曹振中 光金正 张千一 胡郑希 吴仕超 刘景泰 CAO Zhenzhong;GUANG Jinzheng;ZHANG Qianyi;HU Zhengxi;WU Shichao;LIU Jingtai(Institute of Robotics and Automatic Information System,College of Artificial Intelligence,Nankai University,Tianjin 300350,China;Tianjin Key Laboratory of Intelligent Robotics,Tianjin 300350,China;Engineering Research Center of Trusted Behaviour Intelligence,Ministration of Education,Tianjin 300350,China)

机构地区：[1]南开大学人工智能学院机器人与信息自动化研究所,天津300350 [2]天津市智能机器人技术重点实验室,天津300350 [3]可信行为智能算法与系统教育部工程研究中心,天津300350

出　　处：《机器人》2024年第5期611-622,共12页Robot

基　　金：国家自然科学基金(62173189)。

摘　　要：2023年底推出的基于3D高斯溅射的3维重建技术相较于该领域主流传统算法在新视图合成质量和场景渲染速度两方面具有突出优势,本文分析了3D高斯溅射的技术精髓和巨大的应用潜力,全面梳理了基于3D高斯溅射的3维重建技术在视觉SLAM(同步定位与地图构建)、动态场景重建、生成式AI(人工智能)以及自动驾驶领域的应用,最后从科研产出和实际落地两方面展望了3D高斯溅射技术的潜力和技术迭代趋势。The 3D reconstruction technology based on 3D Gaussian splatting(3D GS),launched at the end of 2023,has outstanding advantages in both the quality of new view synthesis and the speed of scene rendering compared to mainstream traditional algorithms in the field.This paper analyzes the essence of the 3D GS technology and its huge potential for application,comprehensively sorting out the application of 3D GS-based 3D reconstruction technology in the field of visual SLAM(simultaneous localization and mapping),dynamic scene reconstruction,generative AI(artificial intelligence),and autonomous driving.Finally,the potential and technological iteration trend of 3D GS technology are discussed from the perspectives of scientific research output and practical implementation.

关 键 词：3D高斯溅射 3维重建 机器人 视觉SLAM(同步定位与地图构建) 动态场景重建 生成式人工智能 自动驾驶 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]