Real-time localization and high-fidelity mapping algorithm for unmanned vehicles driven by 3D Gaussian splatting technology

doi:10.13474/j.cnki.11-2246.2025.1119

Abstract

Abstract: To address the high computational cost and low efficiency of combining neural rendering with SLAM for camera localization and high-fidelity reconstruction,this paper proposes a SLAM algorithm for unmanned vehicles based on 3D Gaussian splatting(3D GS). This algorithm improves localization efficiency through explicit geometric representation and integrates implicit representations to learn illumination and texture to achieve high-precision reconstruction of complex scenes.This method employs a multi-level training strategy based on a Gaussian pyramid to enhance the ability to capture multi-scale details.Experimental results demonstrate excellent performance on multiple datasets,with a 30% improvement in PSNR on the Replica dataset,validating its efficiency and reconstruction quality.

Key words: 3D Gaussian splatting, camera positioning, high-fidelity reconstruction, autonomous vehicles, SLAM

CLC Number:

P208

LU Zhiqiang, PANG Qingkai, WEI Jian. Real-time localization and high-fidelity mapping algorithm for unmanned vehicles driven by 3D Gaussian splatting technology[J]. Bulletin of Surveying and Mapping, 2025, 0(11): 124-128.

References

[1] MUR-ARTAL R,MONTIEL J M M,TARDÓS J D.ORB-SLAM: a versatile and accurate monocular SLAM system[J].IEEE Transactions on Robotics,2015,31(5): 1147-1163.
[2] MUR-ARTAL R,TARDÓS J D.ORB-SLAM2: an open-source SLAM system for monocular,stereo,and RGB-D cameras[J].IEEE Transactions on Robotics,2017,33(5): 1255-1262.
[3] CAMPOS C,ELVIRA R,RODRÍGUEZ J J G,et al.ORB-SLAM3: an accurate open-source library for visual,visual-inertial,and multimap SLAM[J].IEEE Transactions on Robotics,2021,37(6): 1874-1890.
[4] MILDENHALL B,SRINIVASAN P P,TANCIK M,et al.NeRF: representing scenes as neural radiance fields for view synthesis[C]//Proceedings of 2020 Computer Vision-ECCV.Cham: Springer,2020: 405-421.
[5] SUCAR E,LIU Shikun,ORTIZ J,et al.iMAP: implicit mapping and positioning in real-time[C]//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal,QC:IEEE,2021: 6209-6218.
[6] WANG Hengyi,WANG Jingwen,AGAPITO L.Co-SLAM: joint coordinate and sparse parametric encodings for neural real-time SLAM[C]//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023: 13293-13302.
[7] ZHU Zihan,PENG Songyou,LARSSON V,et al.NICE-SLAM: neural implicit scalable encoding for SLAM[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans:IEEE,2022: 12776-12786.
[8] JOHARI M M,CARTA C,FLEURET F.ESLAM: efficient dense SLAM system based on hybrid representation of signed distance fields[C]//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023: 17408-17419.
[9] YANG Xingrui,LI Hai,ZHAI Hongjia,et al.Vox-fusion: dense tracking and mapping with voxel-based neural implicit representation[C]//Proceedings of 2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR).Singapore:IEEE,2022: 499-507.
[10] SANDSTRÖM E,LI Yue,VAN GOOL L,et al.Point-SLAM: dense neural point cloud-based SLAM[C]//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision.Paris:IEEE,2023: 18387-18398.
[11] TEED Z,DENG Jia.RAFT: recurrent all-pairs field transforms for optical flow[M]//Computer Vision-ECCV 2020.Cham: Springer International Publishing,2020: 402-419.
[12] GODARD C,MAC AODHA O,BROSTOW G J.Unsupervised monocular depth estimation with left-right consistency[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017: 6602-6611.
[13] HUANG H,CHEN Y,ZHANG T,et al.360Roam: real-time indoor roaming using geometry-aware 360° radiance fields[EB/OL].[2025-01-19].https://arxiv.org/abs/2208.02705.
[14] FRIDOVICH-KEIL S,YU A,TANCIK M,et al.Plenoxels: radiance fields without neural networks[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans:IEEE,2022: 5491-5500.
[15] RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB: an efficient alternative to SIFT or SURF[C]//Proceedings of 2011 International Conference on Computer Vision.Barcelona:IEEE,2011: 2564-2571.
[16] KERBL B,KOPANAS G,LEIMKUEHLER T,et al.3D Gaussian splatting for real-time radiance field rendering[J].ACM Transactions on Graphics,2023,42(4): 1-14.
[17] CHUNG C M,TSENG Y C,HSU Y C,et al.Orbeez-SLAM: a real-time monocular visual SLAM with ORB features and NeRF-realized mapping[C]//Proceedings of 2023 IEEE International Conference on Robotics and Automation (ICRA).London:IEEE,2023: 9400-9406.
[18] ZHANG Youmin,TOSI F,MATTOCCIA S,et al.GO-SLAM: global optimization for consistent 3D instant reconstruction[C]//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision.Paris:IEEE,2023: 3704-3714.
[19] STURM J,ENGELHARD N,ENDRES F,et al.A benchmark for the evaluation of RGB-D SLAM systems[C]//Proceedings of 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.Vilamoura-Algarve:IEEE,2012: 573-580.
[20] ZHANG R,ISOLA P,EFROS A A,et al.The unreasonable effectiveness of deep features as a perceptual metric[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake city:IEEE,2018: 586-595.