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
  • [21] Efficient convex optimization-based texture mapping for large-scale 3D scene reconstruction
    Sheng, Xin
    Yuan, Jing
    Tao, Wenbing
    Tao, Bo
    Liu, Liman
    INFORMATION SCIENCES, 2021, 556 : 143 - 159
  • [22] Scalable 3D representation for 3D video display in a large-scale space
    Kitahara, I
    Ohta, Y
    IEEE VIRTUAL REALITY 2003, PROCEEDINGS, 2003, : 45 - 52
  • [23] GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lighting
    Li, J.
    Wen, Z.
    Zhang, L.
    Hu, J.
    Hou, F.
    Zhang, Z.
    He, Y.
    Computer Graphics Forum, 2024, 43 (07)
  • [24] Long Range Pooling for 3D Large-Scale Scene Understanding
    Li, Xiang-Li
    Guo, Meng-Hao
    Mu, Tai-Jiang
    Martin, Ralph R.
    Hu, Shi-Min
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 10300 - 10311
  • [25] Deblur-GS: 3D Gaussian Splatting from Camera Motion Blurred Images
    Chen, Wenbo
    Liu, Ligang
    PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES, 2024, 7 (01)
  • [26] Power Bundle Adjustment for Large-Scale 3D Reconstruction
    Weber, Simon
    Demmel, Nikolaus
    Chan, Tin Chon
    Cremers, Daniel
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 281 - 289
  • [27] Large-scale outdoor 3D reconstruction on a mobile device
    Schoeps, Thomas
    Sattler, Torsten
    Hane, Christian
    Pollefeys, Marc
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2017, 157 : 151 - 166
  • [28] SceneDreamer: Unbounded 3D Scene Generation From 2D Image Collections
    Chen, Zhaoxi
    Wang, Guangcong
    Liu, Ziwei
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (12) : 15562 - 15576
  • [29] 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
  • [30] Drone-NeRF: Efficient NeRF based 3D scene reconstruction for large-scale drone survey
    Jia, Zhihao
    Wang, Bing
    Chen, Changhao
    IMAGE AND VISION COMPUTING, 2024, 143
12345