Hierarchical Discrete Distribution Decomposition for Match Density Estimation
CVPR, Volume abs/1812.06264, 2019, Pages 6044-6053.
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
PPT (Upload PPT)