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
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
  • [21] gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction
    Chen, Zerui
    Chen, Shizhe
    Schmid, Cordelia
    Laptev, Ivan
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 12890 - 12900
  • [22] RAMP: Hierarchical Reactive Motion Planning for Manipulation Tasks Using Implicit Signed Distance Functions
    Vasilopoulos, Vasileios
    Garg, Suveer
    Piacenza, Pedro
    Huh, Jinwook
    Isler, Volkan
    2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2023, : 10551 - 10558
  • [23] Large Scale 2D Laser SLAM using Truncated Signed Distance Functions
    Daun, Kevin
    Kohlbrecher, Stefan
    Sturm, Juergen
    von Stryk, Oskar
    2019 IEEE INTERNATIONAL SYMPOSIUM ON SAFETY, SECURITY, AND RESCUE ROBOTICS (SSRR), 2019, : 222 - 228
  • [24] Meshless Monte Carlo radiation transfer method for curved geometries using signed distance functions
    McMillan, Lewis
    Bruce, Graham D.
    Dholakia, Kishan
    JOURNAL OF BIOMEDICAL OPTICS, 2022, 27 (08)
  • [25] Score-Based Generative Models for Medical Image Segmentation Using Signed Distance Functions
    Bogensperger, Lea
    Narnhofer, Dominik
    Ilic, Filip
    Pock, Thomas
    PATTERN RECOGNITION, DAGM GCPR 2023, 2024, 14264 : 3 - 17
  • [26] Large-Scale 3D Semantic Reconstruction for Automated Driving Vehicles with Adaptive Truncated Signed Distance Function
    Hu, Haohao
    Yang, Hexing
    Wu, Jian
    Lei, Xiao
    Bieder, Frank
    Pauls, Jan-Hendrik
    Stiller, Christoph
    2023 IEEE INTELLIGENT VEHICLES SYMPOSIUM, IV, 2023,
  • [27] Signed Distance Function Based Surface Reconstruction of a Submerged Inland Mine Using Continuous-time SLAM
    Bleier, Michael
    Dias, Andre
    Ferreira, Antonio
    Pidgeon, John
    Almeida, Jose
    Silva, Eduardo
    Schilling, Klaus
    Nuechter, Andreas
    IFAC PAPERSONLINE, 2017, 50 (01): : 1139 - 1144
  • [28] Adaptive Reconstruction of a Dynamic Force Using Multiscale Wavelet Shape Functions
    He, Wen-Yu
    Wang, Yang
    Zhu, Songye
    SHOCK AND VIBRATION, 2018, 2018
  • [29] Multi-modal conditional diffusion model using signed distance functions for metal-organic frameworks generation
    Park, Junkil
    Lee, Youhan
    Kim, Jihan
    NATURE COMMUNICATIONS, 2025, 16 (01)
  • [30] Adaptive cross-approximation for surface reconstruction using radial basis functions
    Grzhibovskis, Richards
    Bambach, Markus
    Rjasanow, Sergej
    Hirt, Gerhard
    JOURNAL OF ENGINEERING MATHEMATICS, 2008, 62 (02) : 149 - 160