近年来,3D高斯溅射（3D Gaussian splatting）技术在新视图合成中的应用取得了显著进展,在渲染速度和效率方面取得了极大的成效。与之前的神经辐射场（NeRF）不同,基于神经网络的神经辐射场（NeRF）采用隐式表示。3D高斯溅射技术通过采用一组高斯椭球来进行场景的建模,将这些高斯椭球通过高斯椭球光栅化到图像中,实现高效渲染。这种显式表示方法不仅提升了渲染效率,还为后续的动态重建、几何编辑和物理模拟等任务提供了重要支持。本综述旨在梳理其发展脉络,剖析关键技术,探讨应用现状与挑战,为相关领域研究者提供全面参考。研究进一步指出,3D高斯溅射技术的下一阶段发展,将从追求渲染速度与静态质量的单点突破,转向解决可扩展性、动态真实性、泛化能力与交互智能性等系统级挑战,为数字孪生、混合现实、自主系统等重大应用领域提供核心支撑。
Abstract
In recent years, the application of 3D Gaussian splatting technology in novel view synthesis has made remarkable progress, achieving significant improvements in rendering speed and efficiency. Unlike the previous Neural Radiance Fields (NeRF), which are based on implicit representations, 3D Gaussian splatting models scenes using a set of Gaussian ellipsoids and rasterizes these ellipsoids onto images to achieve efficient rendering. This explicit representation not only enhances rendering efficiency but also provides crucial support for subsequent tasks such as dynamic reconstruction, geometric editing, and physical simulation. This review aims to outline its development trajectory, analyze key technologies, and explore current applications and challenges, providing a comprehensive reference for researchers in related fields. The study further indicates that the next phase of development for 3D Gaussian sputtering technology will shift from pursuing single-point breakthroughs in rendering speed and static quality to addressing system-level challenges such as scalability, dynamic realism, generalization capability, and interactive intelligence. This advancement will provide core support for major application fields including digital twins, mixed reality, and autonomous systems.
关键词
3D高斯溅射技术 /
神经辐射场 /
优化策略 /
渲染质量 /
重建技术
Key words
3D Gauss sputtering technology /
nerve radiation field /
optimization strategy /
render quality /
reconstruction technique
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Luo J,Huang T,Wang W,et al.A Review of Recent Advances in 3D Gaussian Splatting for Optimization and Reconstruction[J].Image and Vision Computing,2024,151:105304.
[2] Franke L,Rückert D,Fink L,et al.TRIPS:Trilinear Point Splatting for Real-Time Radiance Field Rendering[J].Computer Graphics Forum,2024,43(2):e15012.
[3] Zhao C,Huang X,Yang K,et al.Generalizable 3D Gaussian Splatting for Novel View Synthesis[J].Pattern Recognition,2025,161:111271.
[4] Wu T,Yuan Y J,Zhang L X,et al.Recent Advances in 3D Gaussian Splatting[J].Computational Visual Media,2024,10(4):613-642.
[5] Qoyimah S,Sugiastu Firdaus H.A Preliminary Study:Gaussian Splatting Technique in Generating a 3D Model of Textureless Object[J].IOP Conference Series:Earth and Environmental Science,2024,1418(1):012079.
[6] Fei B,Xu J,Zhang R,et al.3D Gaussian Splatting as a New Era:A Survey[J].IEEE Transactions on Visualization and Computer Graphics,2025,31(8):4429-4449.
[7] Zhu H,Zhang Z,Zhao J,et al.Scene Reconstruction Techniques for Autonomous Driving:A Review of 3D Gaussian Splatting[J].Artificial Intelligence Review,2024,58(1):30.
[8] 曹振中,光金正,张千一,等.基于3D高斯溅射的3维重建技术综述[J].机器人,2024,46(5):611-622.
[9] 高建,陈林卓,沈秋,等.基于三维高斯溅射技术的可微分渲染研究进展[J].激光与光电子学进展,2024,61(16):153-165.
[10] 姜金廷,陈斌.基于野外全景视频数据的3D Gaussian Splatting渲染质量评估方法[J].北京大学学报(自然科学版),2025,61(4):733-745.
[11] 乔立贤.基于3D高斯溅射在铁路三维可视化技术应用研究[J].铁道技术标准(中英文),2024,6(8):1-7+16.
[12] 马威,涂强,潘建平,等.桥梁实景三维高斯辐射场建模[J].测绘学报,2024,53(9):1694-1705.
[13] 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.
[14] Cheng K,Long X,Yang K,et al.GaussianPro:3D Gaussian Splatting with Progressive Propagation[EB/OL].2024:arXiv:2402.14650. https://arxiv.org/abs/2402.14650
[15] Zhang J,Zhan F,Xu M,et al.FreGS:3D Gaussian Splatting with Progressive Frequency Regularization[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:21424-21433.
[16] 王博,李少波,潘家兴,等.基于语义嵌入三维高斯溅射的双路径重建算法 [J/OL].计算机应用研究,1-7[2026-01-14].https://doi.org/10.19734/j.issn.1001-3695.2025.06.0263.
[17] Charatan D,Li S L,Tagliasacchi A,et al.PixelSplat:3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:19457-19467.
[18] Fu Y,Wang X,Liu S,et al.COLMAP-Free 3D Gaussian Splatting[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:20796-20805.
[19] Yu Z,Chen A,Huang B,et al.Mip-Splatting:Alias-Free 3D Gaussian Splatting[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:19447-19456.
[20] Yan Z,Low W F,Chen Y,et al.Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:20923-20931.
[21] Jiang Y,Tu J,Liu Y,et al.GaussianShader:3D Gaussian Splatting with Shading Functions for Reflective Surfaces[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:5322-5332.
[22] Malarz D,Smolak-Dyżewska W,Tabor J,et al.Gaussian Splatting with NeRF-Based Color and Opacity[J].Computer Vision and Image Understanding,2025,251:104273.
[23] 刘庭杉,刘伟,张洋,等.基于3D高斯泼溅与语义分割的室内场景三维重建[J].北京信息科技大学学报(自然科学版),2025,40(6):49-58.
[24] Guédon A,Lepetit V.SuGaR:Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:5354-5363.
[25] Yu Z,Sattler T,Geiger A.Gaussian Opacity Fields:Efficient Adaptive Surface Reconstruction in Unbounded Scenes[J].ACM Transactions on Graphics,2024,43(6):1-13.
[26] Szymanowicz S,Rupprecht C,Vedaldi A.Splatter Image:Ultra-Fast Single-View 3D Reconstruction[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:10208-10217.
[27] Zhang C,Zou Y,Li Z,et al.TranSplat:Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers[J].Proceedings of the AAAI Conference on Artificial Intelligence,2025,39(9):9869-9877.
[28] 姜俊超,王永兰,房建东,等.基于3D高斯溅射的复杂室内环境SNGO-SLAM算法 [J/OL].电子测量技术,1-15[2026-01-14].https://link.cnki.net/urlid/11.2175.tn.20251201.0813.002.
[29] 卢志强,庞清凯,魏舰.三维高斯溅射技术驱动的无人车实时定位和高保真建图算法[J].测绘通报,2025(11):124-128.
[30] 马骏,薛旭,陈秉智.基于3D扫描的高速铁路轮对踏面擦伤检测方法[J].机械与电子,2025,43(11):47-53.
[31] 郝东利,于迅博,高鑫,等.基于扩散模型与高斯泼溅的单视图3D光场内容生成 [J/OL].光学学报(网络版),1-20[2026-01-14].https://link.cnki.net/urlid/31.6001.O4. 20251201.0902.006.
[32] Qu Z,Vengurlekar O,Qadri M,et al.Z-Splat:Z-Axis Gaussian Splatting for Camera-Sonar Fusion[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2025,47(9):7255-7267.
[33] Salunke S,Shrivastava A K,Hashmi M F,et al.Quad Key-Secured 3D Gauss Encryption Compression System with Lyapunov Exponent Validation for Digital Images[J].Applied Sciences,2023,13(3):1616.
[34] Qin M,Li W,Zhou J,et al.LangSplat:3D Language Gaussian Splatting[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2024:20051-20060.
[35] Luiten J,Kopanas G,Leibe B,et al.Dynamic 3d gaussians:Tracking by persistent dynamic view synthesis[C]//2024 International Conference on 3D Vision (3DV).IEEE,2024:800-809.
[36] Yang Z,Gao X,Zhou W,et al.Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.2024: 20331-20341.
基金
2025年度校级研究生创新基金项目,编号XY2025096; 河北省体育局2026年度体育科技研究项目,编号2026CY44; 2026年度校级研究生创新基金项目,编号XY2026037
