2018
Manifold Learning in Quotient Spaces
Éloi Mehr, André Lieutier, Fernando Sanchez Bermudez, Vincent Guitteny, Nicolas Thome, Matthieu Cord
CVPR 2018poster
When learning 3D shapes we are usually interested in their intrinsic geometry rather than in their orientation. To deal with the orientation variations the usual trick consists in augmenting the data to exhibit all possible variability, and thus let the model learn both the geometry as well as the r…