DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors

被引:45
作者
Huang, Jiahui [1 ]
Huang, Shi-Sheng [1 ]
Song, Haoxuan [1 ]
Hu, Shi-Min [1 ]
机构
[1] Tsinghua Univ, Dept Comp Sci & Technol, BNRist, Beijing, Peoples R China
来源
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 | 2021年
基金
中国博士后科学基金;
关键词
D O I
10.1109/CVPR46437.2021.00882
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Previous online 3D dense reconstruction methods struggle to achieve the balance between memory storage and surface quality, largely due to the usage of stagnant underlying geometry representation, such as TSDF (truncated signed distance functions) or surfels, without any knowledge of the scene priors. In this paper, we present DI-Fusion (Deep Implicit Fusion), based on a novel 3D representation, i.e. Probabilistic Local Implicit Voxels (PLIVoxs), for online 3D reconstruction with a commodity RGB-D camera. Our PLIVox encodes scene priors considering both the local geometry and uncertainty parameterized by a deep neural network. With such deep priors, we are able to perform online implicit 3D reconstruction achieving state-of-the-art camera trajectory estimation accuracy and mapping quality, while achieving better storage efficiency compared with previous online 3D reconstruction approaches. Our implementation is available at https://www.github.com/huangjh-pub/di-fusion.
引用
收藏
页码:8928 / 8937
页数:10
相关论文
共 54 条
  • [1] [Anonymous], 2018, 3DV, DOI DOI 10.1109/3DV.2018.00015
  • [2] Barfoot T., 2017, STATE ESTIMATION ROB
  • [3] CodeSLAM-Learning a Compact, Optimisable Representation for Dense Visual SLAM
    Bloesch, Michael
    Czarnowski, Jan
    Clark, Ronald
    Leutenegger, Stefan
    Davison, Andrew J.
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 2560 - 2568
  • [4] Real-time High-accuracy Three-Dimensional Reconstruction with Consumer RGB-D Cameras
    Cao, Yan-Pei
    Kobbelt, Leif
    Hu, Shi-Min
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (05):
  • [5] Chabra R, 2020, EUR C COMP VIS, P608, DOI 10.1007
  • [6] Chang A X, 2015, COMPUTER SCI, V1512, P3
  • [7] Chen Jiawen, 2013, ACM Trans. Graph., V32, p113:1
  • [8] BAE-NET: Branched Autoencoder for Shape Co-Segmentation
    Chen, Zhiqin
    Yin, Kangxue
    Fisher, Matthew
    Chaudhuri, Siddhartha
    Zhang, Hao
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 8489 - 8498
  • [9] Learning Implicit Fields for Generative Shape Modeling
    Chen, Zhiqin
    Zhang, Hao
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 5932 - 5941
  • [10] Choi S, 2015, PROC CVPR IEEE, P5556, DOI 10.1109/CVPR.2015.7299195