Corpus ID: 216553723

Single Shot 6D Object Pose Estimation

@article{Kleeberger2020SingleS6,
  title={Single Shot 6D Object Pose Estimation},
  author={Kilian Kleeberger and Marco F. Huber},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.12729}
}
  • Kilian Kleeberger, Marco F. Huber
  • Published 2020
  • Engineering, Computer Science
  • ArXiv
  • In this paper, we introduce a novel single shot approach for 6D object pose estimation of rigid objects based on depth images. For this purpose, a fully convolutional neural network is employed, where the 3D input data is spatially discretized and pose estimation is considered as a regression task that is solved locally on the resulting volume elements. With 65 fps on a GPU, our Object Pose Network (OP-Net) is extremely fast, is optimized end-to-end, and estimates the 6D pose of multiple… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 36 REFERENCES

    Real-Time Seamless Single Shot 6D Object Pose Prediction

    VIEW 1 EXCERPT

    Real-Time Object Pose Estimation with Pose Interpreter Networks

    VIEW 2 EXCERPTS

    3D Pose Regression Using Convolutional Neural Networks

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Picking

    VIEW 2 EXCERPTS

    Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd

    VIEW 1 EXCERPT

    BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL