Probabilistic Volumetric Fusion for Dense Monocular SLAM

被引:8
作者
Rosinol, Antoni [1 ]
Leonard, John J. [1 ]
Carlone, Luca [1 ]
机构
[1] MIT, Cambridge, MA 02139 USA
来源
2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) | 2023年
关键词
D O I
10.1109/WACV56688.2023.00311
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a novel method to reconstruct 3D scenes from images by leveraging deep dense monocular SLAM and fast uncertainty propagation. The proposed approach is able to 3D reconstruct scenes densely, accurately, and in real-time while being robust to extremely noisy depth estimates coming from dense monocular SLAM. Differently from previous approaches, that either use ad-hoc depth filters, or that estimate the depth uncertainty from RGB-D cameras' sensor models, our probabilistic depth uncertainty derives directly from the information matrix of the underlying bundle adjustment problem in SLAM. We show that the resulting depth uncertainty provides an excellent signal to weight the depth-maps for volumetric fusion. Without our depth uncertainty, the resulting mesh is noisy and with artifacts, while our approach generates an accurate 3D mesh with significantly fewer artifacts. We provide results on the challenging Euroc dataset, and show that our approach achieves 92% better accuracy than directly fusing depths from monocular SLAM, and up to 90% improvements compared to the best competing approach.
引用
收藏
页码:3096 / 3104
页数:9
相关论文
共 50 条
  • [21] Monocular Dense Reconstruction by Depth Estimation Fusion
    Chen, Tian
    Ding, Wendong
    Zhang, Dapeng
    Liu, Xilong
    PROCEEDINGS OF THE 30TH CHINESE CONTROL AND DECISION CONFERENCE (2018 CCDC), 2018, : 4460 - 4465
  • [22] Handling pure camera rotation in semi-dense monocular SLAM
    Yao Zhou
    Feihu Yan
    Zhong Zhou
    The Visual Computer, 2019, 35 : 123 - 132
  • [23] A Hybrid Sparse-Dense Monocular SLAM System for Autonomous Driving
    Gallagher, Louis
    Kumar, Varun Ravi
    Yogamani, Senthil
    McDonald, John B.
    10TH EUROPEAN CONFERENCE ON MOBILE ROBOTS (ECMR 2021), 2021,
  • [24] Handling pure camera rotation in semi-dense monocular SLAM
    Zhou, Yao
    Yan, Feihu
    Zhou, Zhong
    VISUAL COMPUTER, 2019, 35 (01) : 123 - 132
  • [25] Fusion of IMU and Vision for Absolute Scale Estimation in Monocular SLAM
    Nuetzi, Gabriel
    Weiss, Stephan
    Scaramuzza, Davide
    Siegwart, Roland
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2011, 61 (1-4) : 287 - 299
  • [26] Densifying SLAM for UAV Navigation by Fusion of Monocular Depth Prediction
    Habib, Yassine
    Papadakis, Panagiotis
    Le Barz, Cedric
    Fagette, Antoine
    Goncalves, Tiago
    Buche, Cedric
    2023 9TH INTERNATIONAL CONFERENCE ON AUTOMATION, ROBOTICS AND APPLICATIONS, ICARA, 2023, : 225 - 229
  • [27] Fusion of IMU and Vision for Absolute Scale Estimation in Monocular SLAM
    Gabriel Nützi
    Stephan Weiss
    Davide Scaramuzza
    Roland Siegwart
    Journal of Intelligent & Robotic Systems, 2011, 61 : 287 - 299
  • [28] Attitude Estimation using Fusion of Monocular SLAM and Inertial Sensors
    Vianchada, C.
    Escamilla, P. J.
    Ibarra, M. N.
    Ramirez, J. M.
    Gomez, P.
    IEEE LATIN AMERICA TRANSACTIONS, 2014, 12 (06) : 977 - 984
  • [29] EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association
    Wu, Yanmin
    Zhang, Yunzhou
    Zhu, Delong
    Feng, Yonghui
    Coleman, Sonya
    Kerr, Dermot
    2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 4966 - 4973
  • [30] Multi-Level Mapping: Real-time Dense Monocular SLAM
    Greene, W. Nicholas
    Ok, Kyel
    Lommel, Peter
    Roy, Nicholas
    2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2016, : 833 - 840