Boundary Cues for 3D Object Shape Recovery

@article{Karsch2013BoundaryCF,
  title={Boundary Cues for 3D Object Shape Recovery},
  author={Kevin Karsch and Zicheng Liao and Jason Rock and Jonathan T. Barron and Derek Hoiem},
  journal={2013 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2013},
  pages={2163-2170}
}
  • Kevin Karsch, Zicheng Liao, +2 authors Derek Hoiem
  • Published in
    IEEE Conference on Computer…
    2013
  • Computer Science
  • Early work in computer vision considered a host of geometric cues for both shape reconstruction and recognition. However, since then, the vision community has focused heavily on shading cues for reconstruction, and moved towards data-driven approaches for recognition. In this paper, we reconsider these perhaps overlooked "boundary" cues (such as self occlusions and folds in a surface), as well as many other established constraints for shape reconstruction. In a variety of user studies and… CONTINUE READING

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

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 22 CITATIONS

    Estimating Coarse 3D Shape and Pose from the Bounding Contour

    VIEW 5 EXCERPTS
    HIGHLY INFLUENCED

    Silhouette Guided Point Cloud Reconstruction beyond Occlusion

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Simultaneous Edge Alignment and Learning

    VIEW 1 EXCERPT
    CITES BACKGROUND

    CASENet: Deep Category-Aware Semantic Edge Detection

    Learning Category-Specific Deformable 3D Models for Object Reconstruction

    VIEW 1 EXCERPT
    CITES BACKGROUND

    A novel cloud surface shape estimation method based on SFS

    • Jiayue Hou
    • Computer Science
    • 2016 5th International Conference on Computer Science and Network Technology (ICCSNT)
    • 2016
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Lifting Object Detection Datasets into 3D

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 19 REFERENCES

    Shape, albedo, and illumination from a single image of an unknown object

    VIEW 5 EXCERPTS

    Efficient Additive Kernels via Explicit Feature Maps

    VIEW 1 EXCERPT

    Depth kernel descriptors for object recognition

    VIEW 3 EXCERPTS

    Indoor scene segmentation using a structured light sensor

    VIEW 1 EXCERPT

    Ground truth dataset and baseline evaluations for intrinsic image algorithms

    VIEW 2 EXCERPTS