Unbounded-GS: Extending 3D Gaussian Splatting With Hybrid Representation for Unbounded Large-Scale Scene Reconstruction

被引：0
|
作者：
Li, Wanzhang [1 ]
Yin, Fukun [1 ]
Liu, Wen [2 ]
Yang, Yiying [3 ]
Chen, Xin [2 ]
Jiang, Biao [1 ]
Yu, Gang [2 ]
Fan, Jiayuan [3 ]
机构：
[1] Fudan University, School Of Information Science And Technology, Shanghai,200433, China
[2] Platform And Content Group (PCG), Tencent, Shanghai,200030, China
[3] Fudan University, Academy For Engineering And Technology, Shanghai,200433, China
来源：
IEEE Robotics and Automation Letters | 2024年 / 9卷 / 12期
关键词：
Modeling large-scale scenes from multi-view images is challenging due to the trade-off dilemma between visual quality and computational cost. Existing NeRF-based methods have made advancements in neural implicit representation through volumetric ray-marching; but still struggle to deal with cubically growing sampling space in large-scale scenes. Fortunately; the rendering approach based on 3D Gaussian splatting (3DGS) has shown promising results; inspiring further exploration in the splatting setting. However; 3DGS has the limitation of inadequate Gaussian points for modeling distant backgrounds; leading to splotchyartifacts. To address this problem; we introduce a novel hybrid neural representation called Unbounded 3D Gaussian. For foreground area; we employs an explicit 3D Gaussian representation to efficiently model the geometry and appearance through splatting weighted Gaussians. For far-away background; we additionally introduce an implicit module comprising Multi-layer Perceptions (MLPs) to directly predict far-away background colors from positional encodings of view positions and ray directions. Furthermore; we design a seamless blending mechanism between the color predictions of the explicit splatting and implicit branches to reconstruct holistic scenes. Extensive experiments demonstrate that our proposed Unbounded-GS inherits the advantages of both faster convergence and high-fidelity rendering quality. © 2016 IEEE;
D O I：
10.1109/LRA.2024.3494652
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：11529 / 11536
相关论文
共 50 条
  • [1] 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
  • [2] 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)
  • [3] Large-Scale 3D Scene Reconstruction with Hilbert Maps
    Guizilini, Vitor
    Ramos, Fabio
    2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016), 2016, : 3247 - 3254
  • [4] A Fast Method for Large-scale Scene Data Acquisition and 3D Reconstruction
    Li, Yao
    Xie, Yang
    Wang, Xijing
    Luo, Xun
    Qi, Yue
    ADJUNCT PROCEEDINGS OF THE 2019 IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY (ISMAR-ADJUNCT 2019), 2019, : 321 - 325
  • [5] Large-scale, real-time 3D scene reconstruction on a mobile device
    Dryanovski, Ivan
    Klingensmith, Matthew
    Srinivasa, Siddhartha S.
    Xiao, Jizhong
    AUTONOMOUS ROBOTS, 2017, 41 (06) : 1423 - 1445
  • [6] Analysis of 3D reconstruction of large-scale architectural scene based on virtual reality
    Li Fang
    Jiang Tao
    Gang Jia-lin
    2017 INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS, ELECTRONICS AND CONTROL (ICCSEC), 2017, : 142 - 146
  • [7] Large-scale, real-time 3D scene reconstruction on a mobile device
    Ivan Dryanovski
    Matthew Klingensmith
    Siddhartha S. Srinivasa
    Jizhong Xiao
    Autonomous Robots, 2017, 41 : 1423 - 1445
  • [8] GS-SFS: Joint Gaussian Splatting and Shape-From-Silhouette for Multiple Human Reconstruction in Large-Scale Sports Scenes
    Jiang, Yuqi
    Li, Jing
    Qin, Haidong
    Dai, Yanran
    Liu, Jing
    Zhang, Guodong
    Zhang, Canbin
    Yang, Tao
    IEEE Transactions on Multimedia, 2024, 26 : 11095 - 11110
  • [9] A review of recent advances in 3D Gaussian Splatting for optimization and reconstruction
    Luo, Jie
    Huang, Tianlun
    Wang, Weijun
    Feng, Wei
    Image and Vision Computing, 2024, 151
  • [10] 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
12345