ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals

@article{Palazzolo2019ReFusion3R,
  title={ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals},
  author={E. Palazzolo and Jens Behley and Philipp Lottes and P. Gigu{\`e}re and C. Stachniss},
  journal={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2019},
  pages={7855-7862}
}
  • E. Palazzolo, Jens Behley, +2 authors C. Stachniss
  • Published 2019
  • Computer Science
  • 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • Mapping and localization are essential capabilities of robotic systems. Although the majority of mapping systems focus on static environments, the deployment in real-world situations requires them to handle dynamic objects. In this paper, we propose an approach for an RGB-D sensor that is able to consistently map scenes containing multiple dynamic elements. For localization and mapping, we employ an efficient direct tracking on the truncated signed distance function (TSDF) and leverage color… CONTINUE READING
    7 Citations
    FullFusion: A Framework for Semantic Reconstruction of Dynamic Scenes
    • 1
    • PDF
    SuMa++: Efficient LiDAR-based Semantic SLAM
    • 19
    • PDF
    Spatio-Temporal Non-Rigid Registration of 3D Point Clouds of Plants
    • 1
    • PDF

    References

    SHOWING 1-10 OF 24 REFERENCES
    DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes
    • 118
    • PDF
    Real-Time Camera Tracking and 3D Reconstruction Using Signed Distance Functions
    • 175
    • PDF
    StaticFusion: Background Reconstruction for Dense RGB-D SLAM in Dynamic Environments
    • 48
    • Highly Influential
    • PDF
    Onboard real-time dense reconstruction of large-scale environments for UAV
    • 11
    • PDF
    Real-time 3D reconstruction at scale using voxel hashing
    • 542
    • PDF
    Real-Time 3D Reconstruction in Dynamic Scenes Using Point-Based Fusion
    • 258
    • Highly Influential
    • PDF
    KinectFusion: Real-time dense surface mapping and tracking
    • 3,069
    • Highly Influential
    • PDF
    Volumetric 3D mapping in real-time on a CPU
    • 127
    • PDF
    MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects
    • Martin Rünz, L. Agapito
    • Computer Science
    • 2018 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)
    • 2018
    • 85
    • Highly Influential
    • PDF
    SDF Tracker: A parallel algorithm for on-line pose estimation and scene reconstruction from depth images
    • 51
    • PDF