3D Shape Segmentation with Projective Convolutional Networks

    CVPR, 2017.

    Cited by: 163|Bibtex|Views16|Links
    EI

    Abstract:

    This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts. Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield coherent segmentations of 3D shapes. The image-based FCNs are used for efficient view-based reasoning a...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments