浏览全部资源
扫码关注微信
网络出版日期： 2024-10-16 ，
移动端阅览
谭臻,牛中颜,张津浦等.SLAM新机遇-高斯溅泼技术[J].中国图象图形学报,
Tan Zhen,Niu Zhongyan,Zhang Jingpu,et al.New Opportunities in SLAM - Gaussian Splatting Technology[J].Journal of Image and Graphics,
同步定位与建图（Simultaneous Localization and Mapping， SLAM）是指在未知环境中同时实现自主移动机器人的定位和环境地图构建的问题，其在机器人技术和自动驾驶等领域有着重要价值。本文首先回顾了SLAM技术的发展历程，从早期的手工特征提取方法到现代的深度学习驱动的解决方案。其中，基于神经辐射场（Neural Radiance Fields， NeRF）的SLAM方法利用神经网络进行场景表征，进一步提高了建图的可视化效果。然而，这类方法在渲染速度上仍然面临挑战，限制了其实时应用的可能性。相比之下，基于高斯溅泼（Gaussian Splatting， GS）的SLAM方法以其实时的渲染速度和照片级的场景渲染效果，为SLAM领域带来了新的研究热点和机遇。接着，文中按照RGB/RGBD、多模态数据以及语义信息三种不同应用类型对基于高斯溅泼的SLAM方法进行了分类和总结，并针对每种情况讨论了相应SLAM方法的优势和局限性。最后，针对当前基于高斯溅泼的SLAM方法面临的实时性、基准一致化、大场景的扩展性以及灾难性遗忘等问题进行分析，并对未来研究方向进行了展望。通过这些探讨和分析，旨在为SLAM领域的研究人员和工程师提供全面的视角和启发，帮助分析和理解当前SLAM系统面临的关键问题，推动该领域的技术进步和应用拓展。
Simultaneous Localization and Mapping （SLAM） has undergone a profound evolution， transitioning through various stages and methodologies， each of which has contributed significantly to advancements in accuracy， robustness， and applicability across diverse scenarios. This paper provides a comprehensive exploration of the historical development and current trends in SLAM， with a particular focus on the progression from manual feature extraction to the adoption of modern deep learning and 3D graphics-based approaches. In the early stages of SLAM development， the process relied heavily on manual feature extraction， where visual features were carefully selected and extracted by human operators to facilitate localization and mapping tasks. While this method proved effective in relatively simple environments， it was highly susceptible to the complexities of more dynamic scenes and variations in illumination. The dependency on human intervention for feature selection not only limited the scalability of these systems but also constrained their robustness in dynamic or unpredictable environments.The introduction of visual SLAM marked a pivotal advancement in the field. By leveraging the rapid progress in computer vision technologies， such as improved feature matching algorithms and visual odometry， visual SLAM systems significantly enhanced both the robustness and accuracy of SLAM. These innovations enabled SLAM systems to perform more reliably across a wide array of real-world environments， thereby paving the way for more automated and efficient approaches to simultaneous localization and mapping. The integration of deep learning into SLAM methodologies represents a paradigm shift in scene understanding and reconstruction. One of the most notable advancements in this area is the emergence of Neural Radiance Fields （NeRF）-based SLAM methods. NeRF-based approaches are capable of modeling dense depth and color information with unprecedented accuracy， providing a more detailed and precise understanding of the environment. However， these methods are not without their challenges， particularly in terms of computational efficiency and real-time performance. Such challenges are especially pertinent in applications where rapid data processing and immediate response are crucial. In response to the limitations of existing SLAM methods， 3D Gaussian Splatting （3DGS） technology has emerged as a promising alternative. 3DGS-based SLAM methods offer significant improvements in rendering speed and high-fidelity scene reconstruction. This technology enhances both the speed and quality of spatial data processing， making it particularly well-suited for applications such as augmented reality and autonomous navigation systems. The inherent robustness of 3DGS-based SLAM methods makes them especially effective in large-scale environments and scenarios characterized by dynamic changes. The categorization of SLAM methodologies can be further refined by considering the types of sensory inputs and the specific application needs they address. Initially， SLAM methods utilizing simple RGB and RGB-D sensors were primarily focused on capturing visual and depth information， which proved effective in controlled environments， particularly indoors. These methods excel in scenarios where there is ample lighting， well-defined textures， and minimal occlusions. However， in more challenging conditions—such as outdoor environments， low-texture or textureless surfaces， and areas with significant lighting variations—RGB and RGB-D SLAM methods often face substantial limitations. For instance， in outdoor environments， changes in lighting， shadows， or exposure to direct sunlight can severely degrade the performance of these methods， leading to inaccuracies in both localization and mapping. Similarly， in textureless regions like white walls or glass surfaces， RGB-D sensors struggle to capture sufficient visual features， resulting in failed or unreliable reconstructions. These limitations underscore the need for more robust SLAM solutions that can operate effectively across a broader range of conditions. Multimodal SLAM approaches have been developed to address these challenges by integrating data from multiple sensors， such as LiDAR， thermal cameras， and inertial measurement units （IMUs）. By combining visual data with other sensory inputs， multimodal SLAM systems can overcome the weaknesses inherent in RGB and RGB-D-based methods. For example， LiDAR can provide accurate depth measurements even in low-light or textureless environments， while thermal cameras can detect heat signatures， aiding in environments where visual data is insufficient or unreliable. Additionally， IMUs contribute to maintaining accurate localization in scenarios with rapid motion or poor visual conditions by providing supplementary motion and orientation data. In scenarios where precise geometric reconstruction and higher-level environmental understanding are required， recent advancements have combined semantic information with SLAM methods based on 3D Gaussian Splatting （3DGS） technology. By incorporating semantic cues， these methods enhance not only the accuracy of scene reconstruction and localization but also provide crucial perceptual information for downstream tasks such as robotic navigation， augmented reality， and embodied intelligence. This integration allows SLAM systems to interpret and adapt to complex， dynamic environments more effectively， making them suitable for a wide range of real-world applications， from indoor mapping to outdoor navigation in varied lighting and textural conditions. The nuanced understanding of when to deploy RGB or RGB-D SLAM versus multimodal SLAM is critical for optimizing the performance and applicability of these systems. While RGB and RGB-D methods are efficient and effective in controlled， well-lit indoor environments， multimodal SLAM approaches are indispensable for applications in outdoor， textureless， or dynamically changing environments where robustness and adaptability are paramount. Despite the significant advancements in SLAM technology， current 3DGS-based methods still face several challenges. These include issues related to scalability in large-scale scenes， adaptability to dynamic environments， and the optimization required for real-time performance. Addressing these challenges is a key focus of ongoing research， which aims to integrate deep learning techniques with traditional geometric methods. Such integration is expected to further enhance the overall performance and versatility of SLAM systems. Additionally， the establishment of unified evaluation benchmarks is crucial for standardizing performance metrics across different SLAM methodologies. Such benchmarks would facilitate greater transparency and comparability in research outcomes， thereby driving further innovation in the field. In conclusion， the evolution of SLAM methodologies—from manual feature extraction to deep learning and 3D graphics-based approaches—has significantly advanced the capabilities of simultaneous localization and mapping systems. By examining the historical developments， current methodologies， and future research directions， this paper provides researchers and engineers with comprehensive insights into the complexities and opportunities associated with advancing SLAM technology. Continued innovation and interdisciplinary collaboration will be essential in driving further advancements， enabling SLAM systems to fulfill their potential across a wide range of practical applications.
同步定位与建图（SLAM）神经辐射场（NeRF）高斯溅泼RGB-（D）多模态语义信息
Simultaneous Localization and Mapping （SLAM）Neural Radiance Fields （NeRF）Gaussian Splatting （GS）RGB-（D）multimodalsemantic information
Barad K R， Richard A， Dentler J， Olivares-Mendez M and Martinez C. 2024. Object-centric Reconstruction and Tracking of Dynamic Unknown Objects using 3D Gaussian Splatting［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2405.20104.pdfhttps://arxiv.org/abs/2405.20104.pdf
Bian W， Wang Z， Li K， Bian J W and Prisacariu V A. 2023. Nope-NeRF： Optimising neural radiance field with no pose prior//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver， Canada： IEEE： 4160-4169［DOI：10.1109/CVPR52729.2023.00405http://dx.doi.org/10.1109/CVPR52729.2023.00405］
Bloesch M， Czarnowski J， Clark R， Leutenegger S and Davison A J. 2018. CodeSLAM—learning a compact， optimisable representation for dense visual SLAM//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City， USA： IEEE： 2560-2568［DOI：10.1109/CVPR.2018.00271http://dx.doi.org/10.1109/CVPR.2018.00271］
Calonder M， Lepetit V， Strecha C and Fua P. 2010. BRIEF： Binary robust independent elementary features//Proceedings of the 11th European Conference on Computer Vision， Part IV. Springer Berlin Heidelberg： Heraklion， Crete， Greece： ECCV： 778-792［DOI：10.1007/978-3-642-15561-1_56http://dx.doi.org/10.1007/978-3-642-15561-1_56］
Chen C， Wang B， Lu C X， Trigoni N and Markham A. 2020. A survey on deep learning for localization and mapping： Towards the age of spatial machine intelligence［EB/OL］.［2024-07-18］. https://arxiv.org/abs/2006.12567.pdfhttps://arxiv.org/abs/2006.12567.pdf
Chen X， Läbe T， Milioto A， Röhling T， Behley J and Stachniss C. 2022. OverlapNet： A siamese network for computing LiDAR scan similarity with applications to loop closing and localization. Autonomous Robots， 1-21［DOI：10.1007/s10514-021-09999-0http://dx.doi.org/10.1007/s10514-021-09999-0］
Chen X， Milioto A， Palazzolo E， Giguere P， Behley J and Stachniss C. 2019. Suma++： Efficient LiDAR-based semantic SLAM//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. Macau， China： IEEE： 4530-4537［DOI：10.1109/IROS40897.2019.8967704http://dx.doi.org/10.1109/IROS40897.2019.8967704］
Dai A， Chang A X， Savva M， Halber M， Funkhouser T and Nießner M. 2017. Scannet： Richly-annotated 3D reconstructions of indoor scenes//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu， USA： IEEE： 5828-5839［DOI：10.1109/CVPR.2017.261http://dx.doi.org/10.1109/CVPR.2017.261］
Deng J， Wu Q， Chen X， Xia S， Sun Z， Liu G， ... and Pei L. 2023. NeRF-LOAM： Neural implicit representation for large-scale incremental LiDAR odometry and mapping//Proceedings of the IEEE/CVF International Conference on Computer Vision. Paris， France： IEEE： 8218-8227［DOI：10.1109/ICCV51070.2023.00755http://dx.doi.org/10.1109/ICCV51070.2023.00755］
Deng T， Chen Y， Zhang L， Yang J， Yuan S， Wang D and Chen W. 2024. Compact 3D Gaussian Splatting for dense visual SLAM［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2403.11247.pdfhttps://arxiv.org/abs/2403.11247.pdf
Derin H， Elliott H， Cristi R and Geman D. 1984. Bayes smoothing algorithms for segmentation of binary images modeled by Markov random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence. 707-720［DOI：10.1109/tpami.1984.4767595http://dx.doi.org/10.1109/tpami.1984.4767595］
Fischler M A and Bolles R C. 1981. Random sample consensus： a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM， 24（6）： 381-395［DOI：10.1145/358669.358692http://dx.doi.org/10.1145/358669.358692］
Forster C， Pizzoli M and Scaramuzza D. 2014. SVO： Fast semi-direct monocular visual odometry//Proceedings of the IEEE International Conference on Robotics and Automation （ICRA）. Hong Kong， China： IEEE： 15-22［DOI：10.1109/ICRA.2014.6906584http://dx.doi.org/10.1109/ICRA.2014.6906584］
Gao X， Zhang T， Liu Y and Yan Q. 2017. 14 lectures on visual SLAM： from theory to practice. Beijing， China： Publishing House of Electronics Industry： 206-234［DOI：10.1007/978-981-16-4939-4http://dx.doi.org/10.1007/978-981-16-4939-4］
Ge Y， Zhang L， Wu Y and Hu D. 2024. PIPO-SLAM： Lightweight Visual-Inertial SLAM With Preintegration Merging Theory and Pose-Only Descriptions of Multiple View Geometry. IEEE Transactions on Robotics， 40： 2046-2059［DOI：10.1109/tro.2024.3366815http://dx.doi.org/10.1109/tro.2024.3366815］
Grisetti G， Kümmerle R， Stachniss C and Burgard W. 2010. A tutorial on graph-based SLAM. IEEE Intelligent Transportation Systems Magazine， 2（4）： 31-43［DOI：10.1109/MITS.2010.939925http://dx.doi.org/10.1109/MITS.2010.939925］
Guo W， Wang B and Chen L. 2024. NeuV-SLAM： Fast Neural Multiresolution Voxel Optimization for RGBD Dense SLAM［EB/OL］.［2024-07-18］. https://arxiv.org/abs/2402.02020.pdfhttps://arxiv.org/abs/2402.02020.pdf
Guo X， Han P， Zhang W and Chen H. 2024. MotionGS： Compact Gaussian Splatting SLAM by Motion Filter［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2405.11129.pdfhttps://arxiv.org/abs/2405.11129.pdf
Hamdi A， Melas-Kyriazi L， Mai J， Qian G， Liu R， Vondrick C， ... and Vedaldi A. 2024. GES： Generalized Exponential Splatting for efficient radiance field rendering//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 19812-19822
Hess W， Kohler D， Rapp H and Andor D. 2016. Real-time loop closure in 2D LIDAR SLAM//Proceedings of the IEEE International Conference on Robotics and Automation （ICRA）. Stockholm， Sweden： IEEE： 1271-1278［DOI：10.1109/ICRA.2016.7487258http://dx.doi.org/10.1109/ICRA.2016.7487258］
Hu J， Chen X， Feng B， Li G， Yang L， Bao H， ... and Cui Z. 2024. CG-SLAM： Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2403.16095.pdfhttps://arxiv.org/abs/2403.16095.pdf
Hu S， Hu T and Liu Z. 2024. GauHuman： Articulated Gaussian Splatting from monocular human videos//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 20418-20431
Hua T， Bai H， Cao Z and Wang L. 2023. Fmapping： Factorized efficient neural field mapping for real-time dense RGB SLAM［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2306.00579.pdfhttps://arxiv.org/abs/2306.00579.pdf
Hua T， Bai H， Cao Z， Liu M， Tao D and Wang L. 2024. Hi-MAP： Hierarchical factorized radiance field for high-fidelity monocular dense mapping［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2401.03203.pdfhttps://arxiv.org/abs/2401.03203.pdf
Huang H， Li L， Cheng H and Yeung S K. 2024. Photo-SLAM： Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 21584-21593
Isaacson S， Kung P C， Ramanagopal M， Vasudevan R and Skinner K A. 2023. Loner： LiDAR only neural representations for real-time SLAM. IEEE Robotics and Automation Letters［J］， 8（12）： 8042-8049［DOI：10.1109/LRA.2023.3324521http://dx.doi.org/10.1109/LRA.2023.3324521］
Ji Y， Liu Y， Xie G， Ma B and Xie Z. 2024. NEDS-SLAM： A novel neural explicit dense semantic SLAM framework using 3D Gaussian Splatting［EB/OL］. arXiv preprint arXiv：2403.11679［2024-03-XX］. https://arxiv.org/abs/2403.11679.pdfhttps://arxiv.org/abs/2403.11679.pdf
Jiang P， Liu H， Li X， Wang T， Zhang F and Buhmann J M. 2024. TAMBRIDGE： Bridging Frame-Centered Tracking and 3D Gaussian Splatting for Enhanced SLAM［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2405.19614.pdfhttps://arxiv.org/abs/2405.19614.pdf
Jiang P， Pandey G and Saripalli S. 2024. 3DGS-ReLoc： 3D Gaussian Splatting for Map Representation and Visual ReLocalization［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2403.11367.pdfhttps://arxiv.org/abs/2403.11367.pdf
Jin L， Chen X， Rückin J and Popović M. 2023. Neu-NBV： Next best view planning using uncertainty estimation in image-based neural rendering//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Detroit， USA： IEEE： 11305-11312［DOI：10.1109/IROS55552.2023.10342226http://dx.doi.org/10.1109/IROS55552.2023.10342226］
Kalman R E and Bucy R S. 1961. New results in linear filtering and prediction theory［J］. 95-108［DOI：10.1115/1.3658902http://dx.doi.org/10.1115/1.3658902］
Keetha N， Karhade J， Jatavallabhula K M， Yang G， Scherer S， Ramanan D and Luiten J. 2024. SplaTAM： Splat Track & Map 3D Gaussians for Dense RGB-D SLAM//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 21357-21366
Kerbl B， Kopanas G， Leimkühler T and Drettakis G. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics， 42（4）： 139-1［DOI：10.1145/3592433http://dx.doi.org/10.1145/3592433］
Klein G and Murray D. 2007. Parallel tracking and mapping for small AR workspaces//Proceedings of the 6th IEEE and ACM International Symposium on Mixed and Augmented Reality. Nara， Japan： IEEE： 225-234［DOI：10.1109/ISMAR.2007.4538852http://dx.doi.org/10.1109/ISMAR.2007.4538852］
Lan T， Lin Q and Wang H. 2024. Monocular Gaussian SLAM with Language Extended Loop Closure［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2405.13748.pdfhttps://arxiv.org/abs/2405.13748.pdf
Lang X， Li L， Zhang H， Zong F， Xu M， Liu Y， ... and Lv J. 2024. Gaussian-LIC： Photo-realistic LiDAR-Inertial-Camera SLAM with 3D Gaussian Splatting［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2404.06926.pdfhttps://arxiv.org/abs/2404.06926.pdf
Leonard J J and Durrant-Whyte H F. 1991. Simultaneous map building and localization for an autonomous mobile robot//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. Vol. 3： Osaka， Japan： IEEE： 1442-1447［DOI：10.1109/IROS.1991.174711http://dx.doi.org/10.1109/IROS.1991.174711］
Li H， Gu X， Yuan W， Yang L， Dong Z and Tan P. 2023. Dense RGB SLAM with neural implicit maps［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2301.08930.pdfhttps://arxiv.org/abs/2301.08930.pdf
Li J， Zhang J， Bai X， Zheng J， Ning X， Zhou J and Gu L. 2024. DnGaussian： Optimizing sparse-view 3D Gaussian radiance fields with global-local depth normalization//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 20775-20785
Li M， Huang J， Sun L， Tian A X， Deng T and Wang H. 2024. NGM-SLAM： Gaussian Splatting SLAM with Radiance Field Submap［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2405.05702.pdfhttps://arxiv.org/abs/2405.05702.pdf
Li M， Liu S and Zhou H. 2024. SGS-SLAM： Semantic Gaussian Splatting for neural dense SLAM［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2402.03246.pdfhttps://arxiv.org/abs/2402.03246.pdf
Li S， Chen X， Liu Y， Dai D， Stachniss C and Gall J. 2021. Multi-scale interaction for real-time LiDAR data segmentation on an embedded platform. IEEE Robotics and Automation Letters， 7（2）： 738-745［DOI：10.1109/LRA.2021.3132059http://dx.doi.org/10.1109/LRA.2021.3132059］
Li Y， Brasch N， Wang Y， Navab N and Tombari F. 2020. Structure-SLAM： Low-drift monocular SLAM in indoor environments. IEEE Robotics and Automation Letters， 5（4）： 6583-6590［DOI：10.1109/LRA.2020.3015456http://dx.doi.org/10.1109/LRA.2020.3015456］
Li Z， Chen Z， Li Z and Xu Y. 2024. Spacetime Gaussian Feature Splatting for real-time dynamic view synthesis//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 8508-8520
Liu R， Wang X， Zhang C and Zhang B. 2020. A Survey on Visual SLAM based on Deep Learning. Journal of System Simulation， 32（7）： 1244-1256
刘瑞军， 王向上， 张晨， 章博华. 2020. 基于深度学习的视觉SLAM综述. 系统仿真学报， 32（7）： 1244-1256［DOI：10.16182/j.issn1004731x.joss.19-VR0466http://dx.doi.org/10.16182/j.issn1004731x.joss.19-VR0466］
Matsuki H， Murai R， Kelly P H and Davison A J. 2024. Gaussian Splatting SLAM//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 18039-18048
Mildenhall B， Srinivasan P P， Tancik M， Barron J T， Ramamoorthi R and Ng R. 2021. NeRF： Representing scenes as neural radiance fields for view synthesis. Communications of the ACM， 65（1）： 99-106［DOI：10.1007/978-3-030-58452-8_24http://dx.doi.org/10.1007/978-3-030-58452-8_24］
Montemerlo M， Thrun S， Koller D and Wegbreit B. 2002. FastSLAM： A factored solution to the simultaneous localization and mapping problem//AAAI/IAAI. Edmonton， Canada： AAAI： 593-598［DOI：10.5555/1630659.1630824http://dx.doi.org/10.5555/1630659.1630824］
Mur-Artal R， Montiel J M M and Tardos J D. 2015. ORB-SLAM： a versatile and accurate monocular SLAM system. IEEE Transactions on Robotics， 31（5）： 1147-1163［DOI：10.1109/TRO.2015.2463671http://dx.doi.org/10.1109/TRO.2015.2463671］
Niedermayr S， Stumpfegger J and Westermann R. 2024. Compressed 3D Gaussian Splatting for accelerated novel view synthesis//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 10349-10358
Pan X， Liu H， Fang M， Wang Z， Zhang Y and Zhang G. 2023. Dynamic 3D scenario-oriented monocular SLAM based on semantic probability prediction. Journal of Image and Graphics， 28（7）， 2151-2166.
潘小鹍， 刘浩敏， 方铭， 王政， 张涌， 章国锋. 2023. 基于语义概率预测的动态场景单目视觉 SLAM. 中国图象图形学报， 28（7）， 2151-2166.［DOI：10.11834/jig.210632http://dx.doi.org/10.11834/jig.210632］
Pan Y， Zhong X， Wiesmann L， Posewsky T， Behley J and Stachniss C. 2024. PIN-SLAM： LiDAR SLAM using a point-based implicit neural representation for achieving global map consistency［EB/OL］.［2024-07-18］. https://arxiv.org/abs/2401.09101.pdfhttps://arxiv.org/abs/2401.09101.pdf
Peng Z， Shao T， Liu Y， Zhou J， Yang Y， Wang J and Zhou K. 2024. RTG-SLAM： Real-time 3D Reconstruction at Scale using Gaussian Splatting//ACM SIGGRAPH 2024 Conference Papers. Colorado， USA： ACM： 1-11［DOI：10.1145/3641519.3657455http://dx.doi.org/10.1145/3641519.3657455］
Qin T， Li P and Shen S. 2018. VINS-Mono： A robust and versatile monocular visual-inertial state estimator. IEEE Transactions on Robotics， 34（4）： 1004-1020［DOI：10.1109/TRO.2018.2853729http://dx.doi.org/10.1109/TRO.2018.2853729］
Rosten E and Drummond T. 2006. Machine learning for high-speed corner detection//Proceedings of the 9th European Conference on Computer Vision， Part I. Springer Berlin Heidelberg： Graz， Austria： ECCV： 430-443［DOI：10.1007/11744023_34http://dx.doi.org/10.1007/11744023_34］
Rublee E， Rabaud V， Konolige K and Bradski G. 2011. ORB： An efficient alternative to SIFT or SURF//Proceedings of the International Conference on Computer Vision. Barcelona， Spain： IEEE： 2564-2571［DOI：10.1109/ICCV.2011.6126544http://dx.doi.org/10.1109/ICCV.2011.6126544］
Sandström E， Tateno K， Oechsle M， Niemeyer M， Van Gool L， Oswald M R and Tombari F. 2024. Splat-SLAM： Globally Optimized RGB-only SLAM with 3D Gaussians［EB/OL］.［2024-07-18］. https://arxiv.org/abs/2405.16544.pdfhttps://arxiv.org/abs/2405.16544.pdf
Simmons R and Koenig S. 1995. Probabilistic Robot Navigation in Partially Observable Environments［J］
Smith R C and Cheeseman P. 1986. On the representation and estimation of spatial uncertainty. The International Journal of Robotics Research， 5（4）： 56-68［DOI：10.1177/027836498600500404http://dx.doi.org/10.1177/027836498600500404］
Song X， Zheng J， Yuan S， Gao H A， Zhao J， He X， ... and Zhao H. 2024. SA-GS： Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing［EB/OL］.［2024-07-18］. https://arxiv.org/abs/2403.19615.pdfhttps://arxiv.org/abs/2403.19615.pdf
Straub J， Whelan T， Ma L， Chen Y， Wijmans E， Green S， ... and Newcombe R. 2019. The Replica dataset： A digital replica of indoor spaces［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/1906.05797.pdfhttps://arxiv.org/abs/1906.05797.pdf
Sucar E， Liu S， Ortiz J and Davison A J. 2021. iMAP： Implicit mapping and positioning in real-time//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal， Canada： IEEE： 6229-6238［DOI：10.1109/ICCV48922.2021.00617http://dx.doi.org/10.1109/ICCV48922.2021.00617］
Sun L C， Bhatt N P， Liu J C， Fan Z， Wang Z， Humphreys T E and Topcu U. 2024. MM3DGS SLAM： Multi-modal 3D Gaussian Splatting for SLAM Using Vision， Depth， and Inertial Measurements［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2404.00923.pdfhttps://arxiv.org/abs/2404.00923.pdf
Sun S， Mielle M， Lilienthal A J and Magnusson M. 2024. High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2403.12535.pdfhttps://arxiv.org/abs/2403.12535.pdf
Tan Z， Zhou Z， Ge Y， Wang Z， Chen X and Hu D. 2024. TD-NeRF： Novel Truncated Depth Prior for Joint Camera Pose and Neural Radiance Field Optimization［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2405.07027.pdfhttps://arxiv.org/abs/2405.07027.pdf
Tateno K， Tombari F， Laina I and Navab N. 2017. CNN-SLAM： Real-time dense monocular SLAM with learned depth prediction//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu， USA： IEEE： 6243-6252［DOI：10.1109/CVPR.2017.695http://dx.doi.org/10.1109/CVPR.2017.695］
Teigen A L， Park Y， Stahl A and Mester R. 2024. RGB-D mapping and tracking in a plenoxel radiance field//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa， USA： IEEE： 3342-3351［DOI：10.1109/WACV57701.2024.00331http://dx.doi.org/10.1109/WACV57701.2024.00331］
Thrun S. 2002. Particle Filters in Robotics//UAI. Vol. 2： 511-518［DOI：10.5555/2073876.2073937http://dx.doi.org/10.5555/2073876.2073937］
Tosi F， Zhang Y， Gong Z， Sandström E， Mattoccia S， Oswald M R and Poggi M. 2024. How NeRFs and 3D Gaussian Splatting are reshaping SLAM： a survey［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2402.13255.pdfhttps://arxiv.org/abs/2402.13255.pdf
Wang J， Zuo X， Zhao X， Lv J and Liu Y. 2022. Review of multi-source fusion SLAM： current status and challenges. Journal of Image and Graphics， 28（2）
王金科， 左星星， 赵祥瑞， 吕佳俊， 刘勇. 2022. 多源融合SLAM的现状与挑战. 中国图象图形学报， 28（2）.［DOI： 10.11834/jig.210547http://dx.doi.org/10.11834/jig.210547］
Wang K， Yang C， Wang Y， Li S， Wang Y， Dou Q， ... and Shen W. 2024. EndoGSLAM： Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2403.15124.pdfhttps://arxiv.org/abs/2403.15124.pdf
Wang Z， Wu S， Xie W， Chen M and Prisacariu V A. 2021. NeRF--： Neural radiance fields without known camera parameters［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2102.07064.pdfhttps://arxiv.org/abs/2102.07064.pdf
Wu C， Duan Y， Zhang X， Sheng Y， Ji J and Zhang Y. 2024. MM-Gaussian： 3D Gaussian-based Multi-modal Fusion for Localization and Reconstruction in Unbounded Scenes［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2404.04026.pdfhttps://arxiv.org/abs/2404.04026.pdf
Yan C， Qu D， Xu D， Zhao B， Wang Z， Wang D and Li X. 2024. GS-SLAM： Dense visual SLAM with 3D Gaussian Splatting//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 19595-19604
Yang Z， Gao X， Zhou W， Jiao S， Zhang Y and Jin X. 2024. Deformable 3D Gaussians for high-fidelity monocular dynamic scene reconstruction//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， USA： IEEE： 20331-20341
Yugay V， Li Y， Gevers T and Oswald M R. 2023. Gaussian-SLAM： Photo-realistic dense SLAM with Gaussian Splatting［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2312.10070.pdfhttps://arxiv.org/abs/2312.10070.pdf
Zhu P， Zhuang Y， Chen B， Li L， Wu C and Liu Z. 2024. MGS-SLAM： Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2405.06241.pdfhttps://arxiv.org/abs/2405.06241.pdf
Zhu S， Qin R， Wang G， Liu J and Wang H. 2024. SemGauss-SLAM： Dense semantic Gaussian splatting SLAM［EB/OL］. ［2024-07-18］. https://arxiv.org/abs/2403.07494.pdfhttps://arxiv.org/abs/2403.07494.pdf
Zhu Z， Peng S， Larsson V， Xu W， Bao H， Cui Z， ... and Pollefeys M. 2022. NICE-SLAM： Neural implicit scalable encoding for SLAM//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans， USA： IEEE： 12786-12796［DOI：10.1109/CVPR52688.2022.01245http://dx.doi.org/10.1109/CVPR52688.2022.01245］
相关作者
相关机构
京公网安备11010802024621