OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees

被引:0
|
作者
Kim, Hakyeong [1 ]
Meuleman, Andreas [2 ]
Jang, Hyeonjoong [1 ]
Tompkin, James [3 ]
Kim, Min H. [1 ]
机构
[1] Korea Adv Inst Sci & Technol, Daejeon, South Korea
[2] INRIA, Paris, France
[3] Brown Univ, Providence, RI USA
来源
2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2024年
关键词
D O I
10.1109/CVPR52733.2024.01912
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 method to reconstruct indoor and outdoor static scene geometry and appearance from an omnidirectional video moving in a small circular sweep. This setting is challenging because of the small baseline and large depth ranges, making it difficult to find ray crossings. To better constrain the optimization, we estimate geometry as a signed distance field within a spherical binoctree data structure and use a complementary efficient tree traversal strategy based on a breadth-first search for sampling. Unlike regular grids or trees, the shape of this structure well-matches the camera setting, creating a better memory-quality trade-off. From an initial depth estimate, the binoctree is adaptively subdivided throughout the optimization; previous methods use a fixed depth that leaves the scene undersampled. In comparison with three neural optimization methods and two non-neural methods, ours shows decreased geometry error on average, especially in a detailed scene, while significantly reducing the required number of voxels to represent such details.
引用
收藏
页码:20227 / 20236
页数:10
相关论文
共 44 条
  • [31] Adaptive cross-approximation for surface reconstruction using radial basis functions
    Richards Grzhibovskis
    Markus Bambach
    Sergej Rjasanow
    Gerhard Hirt
    Journal of Engineering Mathematics, 2008, 62 : 149 - 160
  • [32] On the Road to Large-Scale 3D Monocular Scene Reconstruction using Deep Implicit Functions
    Roddick, Thomas
    Biggs, Benjamin
    Reino, Daniel Olmeda
    Cipolla, Roberto
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021), 2021, : 2875 - 2884
  • [33] Surface Reconstruction of Scanned Human Body Using Radial Basis Functions and Adaptive Partition of Unity
    吕方梅
    习俊通
    马登哲
    Journal of Shanghai Jiaotong University(Science), 2009, 14 (03) : 261 - 265
  • [34] Surface reconstruction of scanned human body using radial basis functions and adaptive partition of unity
    Lü F.-M.
    Xi J.-T.
    Ma D.-Z.
    Journal of Shanghai Jiaotong University (Science), 2009, 14 (3) : 261 - 265
  • [35] Adaptive vision-based crack detection using 3D scene reconstruction for condition assessment of structures
    Jahanshahi, Mohammad R.
    Masri, Sami F.
    AUTOMATION IN CONSTRUCTION, 2012, 22 : 567 - 576
  • [36] Random Normal Matching: A Robust Probability-Based 2D Scan Matching Approach Using Truncated Signed Distance Functions
    Ammon, Daniel
    Fink, Tobias
    May, Stefan
    2017 IEEE INTERNATIONAL CONFERENCE ON AUTONOMOUS ROBOT SYSTEMS AND COMPETITIONS (ICARSC), 2017, : 222 - 227
  • [37] CHISEL: Real Time Large Scale 3D Reconstruction Onboard a Mobile Device using Spatially-Hashed Signed Distance Fields
    Klingensmith, Matthew
    Dryanovski, Ivan
    Srinivasa, Siddhartha S.
    Xiao, Jizhong
    ROBOTICS: SCIENCE AND SYSTEMS XI, 2015,
  • [38] Real-Time Tracking of Single and Multiple Objects from Depth-Colour Imagery Using 3D Signed Distance Functions
    C. Y. Ren
    V. A. Prisacariu
    O. Kähler
    I. D. Reid
    D. W. Murray
    International Journal of Computer Vision, 2017, 124 : 80 - 95
  • [39] Real-Time Tracking of Single and Multiple Objects from Depth-Colour Imagery Using 3D Signed Distance Functions
    Ren, C. Y.
    Prisacariu, V. A.
    Kahler, O.
    Reid, I. D.
    Murray, D. W.
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2017, 124 (01) : 80 - 95
  • [40] Multi-Cam ARM-SLAM: Robust Multi-Modal State Estimation Using Truncated Signed Distance Functions for Mobile Rescue Robots
    Suess, Jasper
    Schnaubelt, Marius
    von Stryk, Oskar
    2022 IEEE INTERNATIONAL SYMPOSIUM ON SAFETY, SECURITY, AND RESCUE ROBOTICS (SSRR), 2022, : 293 - 299