Hierarchical Discrete Distribution Decomposition for Match Density Estimation

    Zhichao Yin
    Zhichao Yin

    CVPR, Volume abs/1812.06264, 2019, Pages 6044-6053.

    Cited by: 40|Bibtex|Views35|Links
    EI

    Abstract:

    Existing deep learning methods for pixel correspondence output a point estimate of the motion field, but do not represent the full match distribution. Explicit representation of a match distribution is desirable for many applications as it allows direct representation of the correspondence probability. The main difficulty of estimating a ...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments