机器人2026，Vol.48Issue(1)：116-124,9.DOI:10.13973/j.cnki.robot.240193
基于知识蒸馏的NeRF SLAM模型轻量化研究
Research on Lightweight NeRF SLAM Models through Knowledge Distillation
摘要
Abstract
NeRF(neural radiance field)has great potential in high-quality 3D scene reconstruction.However,its high computational complexity,data requirements,and storage limitations pose numerous challenges in practical applications.To tackle this issue,an improved NeRF-based SLAM(simultaneous localization and mapping)system incorporating knowledge distillation is proposed to achieve rapid and efficient training.The experimental results show that the proposed system improves the point cloud accuracy by 18.21％,the point cloud completeness by 14.86％,and the completion rate by 14.09％in terms of reconstruction accuracy,compared with the original NeRF model.In terms of reconstruction efficiency,it reduces the total FLOPs(floating point operations)by 35.52％.While maintaining the reconstruction accuracy,it significantly reduces the training time and computational resource consumption.This research not only offers new insights for optimizing NeRF SLAM systems,but also opens new paths for the application of knowledge distillation to the 3D vision domain.关键词
NeRF(神经辐射场)/SLAM(同步定位与地图构建)/知识蒸馏/3维场景重建/训练优化Key words
NeRF(neural radiance field)/SLAM(simultaneous localization and mapping)/knowledge distillation/3D scene reconstruction/training optimization引用本文复制引用
王红星,罗子杰,吴欢娣,曹雏清,徐劲松,刘国满,邓少波,叶展..基于知识蒸馏的NeRF SLAM模型轻量化研究[J].机器人,2026,48(1):116-124,9.基金项目
江西水利电力大学博士科研启动项目(2022kyqd027) （2022kyqd027）
2024年度学位与研究生教育教学改革研究项目(NGYJG-2024-001) （NGYJG-2024-001）
大规模个性化定制系统与技术全国重点实验室开放课题(MPC-2024-01-01) （MPC-2024-01-01）
江西水利电力大学一流课程(南工教字[2023]29号——机器人技术基础) （南工教字[2023]29号——机器人技术基础）
江西省教育厅自然科学基金(20224BAB202014). （20224BAB202014）
