A review of recent advances in 3D Gaussian Splatting for optimization and reconstruction

被引：0
|
作者：
Luo, Jie [1 ,2 ]
Huang, Tianlun [1 ,2 ]
Wang, Weijun [1 ,2 ]
Feng, Wei [1 ,2 ]
机构：
[1] Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
[2] University of Chinese Academy of Sciences, Beijing, China
来源：
Image and Vision Computing | 2024年 / 151卷
关键词：
3D Gaussian Splatting (3DGS) represents a significant breakthrough in computer graphics and vision; offering an explicit scene representation and novel view synthesis without the reliance on neural networks; unlike Neural Radiance Fields (NeRF). This paper provides a comprehensive survey of recent research on 3DGS optimization and reconstruction; with a particular focus on studies featuring published or forthcoming open-source code. In terms of optimization; the paper examines techniques such as compression; densification; splitting; anti-aliasing; and reflection enhancement. For reconstruction; it explores methods including surface mesh extraction; sparse-view object and scene reconstruction; large-scale scene reconstruction; and dynamic object and scene reconstruction. Through comparative analysis and case studies; the paper highlights the practical advantages of 3DGS and outlines future research directions; offering valuable insights for advancing the field. © 2024 Elsevier B.V;
D O I：
10.1016/j.imavis.2024.105304
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 50 条
  • [1] Recent advances in 3D Gaussian splatting
    Wu, Tong
    Yuan, Yu-Jie
    Zhang, Ling-Xiao
    Yang, Jie
    Cao, Yan-Pei
    Yan, Ling-Qi
    Gao, Lin
    COMPUTATIONAL VISUAL MEDIA, 2024, 10 (04) : 613 - 642
  • [2] Gaussian Splatting: 3D Reconstruction and Novel View Synthesis: A Review
    Dalal, Anurag
    Hagen, Daniel
    Robbersmyr, Kjell G.
    Knausgard, Kristian Muri
    IEEE ACCESS, 2024, 12 : 96797 - 96820
  • [3] Scene reconstruction techniques for autonomous driving: a review of 3D Gaussian splatting
    Huixin Zhu
    Zhili Zhang
    Junyang Zhao
    Hui Duan
    Yao Ding
    Xiongwu Xiao
    Junsong Yuan
    Zhang, Zhili (157918018@qq.com); Zhao, Junyang (zhaojy802@sina.com), 2025, 58 (01)
  • [4] 3D Gaussian Splatting with Deferred Reflection
    Ye, Keyang
    Hou, Qiming
    Zhou, Kun
    PROCEEDINGS OF SIGGRAPH 2024 CONFERENCE PAPERS, 2024,
  • [5] Large-Scale 3D Terrain Reconstruction Using 3D Gaussian Splatting for Visualization and Simulation
    Chen, Meida
    Lal, Devashish
    Yu, Zifan
    Xu, Jiuyi
    Feng, Andrew
    You, Suya
    Nurunnabi, Abdul
    Shi, Yangming
    MID-TERM SYMPOSIUM THE ROLE OF PHOTOGRAMMETRY FOR A SUSTAINABLE WORLD, VOL. 48-2, 2024, : 49 - 54
  • [6] The Potential of Neural Radiance Fields and 3D Gaussian Splatting for 3D Reconstruction from Aerial Imagery
    Haitz, Dennis
    Hermann, Max
    Roth, Aglaja Solana
    Weinmann, Michael
    Weinmann, Martin
    ISPRS ANNALS OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES: VOLUME X-2-2024, 2024, : 97 - 104
  • [7] Reducing the Memory Footprint of 3D Gaussian Splatting
    Papantonakis, Panagiotis
    Kopanas, Georgios
    Kerbl, Bernhard
    Lanvin, Alexandre
    Drettakis, George
    PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES, 2024, 7 (01)
  • [8] Privacy-Preserving 3D Gaussian Splatting
    Ali, Usman
    2024 IEEE GAMING, ENTERTAINMENT, AND MEDIA CONFERENCE, GEM 2024, 2024, : 385 - 387
  • [9] Impact of Camera Settings on 3D Reconstruction Quality: Insights from NeRF and Gaussian Splatting
    Rangelov, Dimitar
    Waanders, Sierd
    Waanders, Kars
    van Keulen, Maurice
    Miltchev, Radoslav
    Sensors, 2024, 24 (23)
  • [10] Recent advances in 3D SEM surface reconstruction
    Tafti, Ahmad P.
    Kirkpatrick, Andrew B.
    Alavi, Zahrasadat
    Owen, Heather A.
    Yu, Zeyun
    MICRON, 2015, 78 : 54 - 66
12345