3D-RelNet: Joint Object and Relational Network for 3D Prediction

@article{Kulkarni20193DRelNetJO,
  title={3D-RelNet: Joint Object and Relational Network for 3D Prediction},
  author={Nilesh Kulkarni and Ishan Misra and Shubham Tulsiani and Abhinav Gupta},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={2212-2221}
}
  • Nilesh Kulkarni, Ishan Misra, +1 author Abhinav Gupta
  • Published in
    IEEE/CVF International…
    2019
  • Computer Science
  • We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them. We argue that reasoning about these relationships is crucial, and present an approach to incorporate these in a 3D prediction framework. In addition to independent per-object predictions, we predict pairwise relations in the form of relative 3D pose, and… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES

    Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene

    VIEW 10 EXCERPTS

    Semi-Supervised Classification with Graph Convolutional Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare

    VIEW 1 EXCERPT

    6-DoF object pose from semantic keypoints

    VIEW 1 EXCERPT