NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping

被引:11
|
作者
Lionar, Stefan [1 ]
Schmid, Lukas [1 ]
Cadena, Cesar [1 ]
Siegwart, Roland [1 ]
Cramariuc, Andrei [1 ]
机构
[1] Swiss Fed Inst Technol, Autonomous Syst Lab, Zurich, Switzerland
关键词
D O I
10.1109/3DV53792.2021.00135
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 3D mapping method leveraging the recent progress in neural implicit representation for 3D reconstruction. Most existing state-of-the-art neural implicit representation methods are limited to object-level reconstructions and can not incrementally perform updates given new data. In this work, we propose a fusion strategy and training pipeline to incrementally build and update neural implicit representations that enable the reconstruction of large scenes from sequential partial observations. By representing an arbitrarily sized scene as a grid of latent codes and performing updates directly in latent space, we show that incrementally built occupancy maps can be obtained in real-time even on a CPU. Compared to traditional approaches such as Truncated Signed Distance Fields (TSDFs), our map representation is significantly more robust in yielding a better scene completeness given noisy inputs. We demonstrate the performance of our approach in thorough experimental validation on real-world datasets with varying degrees of added pose noise.
引用
收藏
页码:1279 / 1289
页数:11
相关论文
共 50 条
  • [21] Fusion Approach for Real-Time Mapping Street Atmospheric Pollution Concentration
    Lv, Wenjun
    Kang, Yu
    Li, Zerui
    Zhao, Yunbo
    2016 9TH INTERNATIONAL CONFERENCE ON HUMAN SYSTEM INTERACTIONS (HSI), 2016, : 133 - 139
  • [22] An Efficient Volumetric Mesh Representation for Real-time Scene Reconstruction using Spatial Hashing
    Dong, Wei
    Shi, Jieqi
    Tang, Weijie
    Wang, Xin
    Zha, Hongbin
    2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 6323 - 6330
  • [23] A hybrid representation for modeling, interactive editing, and real-time visualization of terrains with volumetric features
    Koca, Cetin
    Gudukbay, Ugur
    INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE, 2014, 28 (09) : 1821 - 1847
  • [24] Synthesising Light Field Volumetric Visualizations in Real-time using a Compressed Volume Representation
    Bruton, Sean
    Ganter, David
    Manzke, Michael
    PROCEEDINGS OF THE 14TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL 3: IVAPP, 2019, : 96 - 105
  • [25] Towards Real-Time Neural Volumetric Rendering on Mobile Devices: A Measurement Study
    Wang, Zhe
    Zhu, Yifei
    PROCEEDINGS OF THE 2024 SIGCOMM WORKSHOP ON EMERGING MULTIMEDIA SYSTEMS, EMS 2024, 2024, : 8 - 13
  • [26] Local map fusion for real-time indoor simultaneous localization and mapping
    Rodriguez-Losada, Diego
    Matia, Fernando
    Jimenez, Agustin
    Galan, Ramon
    JOURNAL OF FIELD ROBOTICS, 2006, 23 (05) : 291 - 309
  • [27] Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering
    Hu, Dongting
    Zhang, Zhenkai
    Hou, Tingbo
    Liu, Tongliang
    Fu, Huan
    Gong, Mingming
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 17726 - 17737
  • [28] Real-Time Volumetric Perception for Unmanned Surface Vehicles Through Fusion of Radar and Camera
    Xu, Hu
    Zhang, Xiaomin
    He, Ju
    Yu, Yang
    Cheng, Yuwei
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 : 1 - 12
  • [29] Tiny Fusion: Tiny Deep Convolutional Neural Network for Real-time Image Fusion
    Wang, Jixiao
    Li, Yang
    Miao, Zhuang
    Wang, Jiabao
    Zhao, Xun
    2019 2ND IEEE INTERNATIONAL CONFERENCE ON INFORMATION COMMUNICATION AND SIGNAL PROCESSING (ICICSP), 2019, : 384 - 389
  • [30] Scene data fusion: Real-time standoff volumetric gamma-ray imaging
    Barnowski, Ross
    Haefner, Andrew
    Mihailescu, Lucian
    Vetter, Kai
    NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2015, 800 : 65 - 69