# Manifold Learning in Quotient Spaces

Ãloi MehrAndrÃ© LieutierFernando Sanchez BermudezVincent GuittenyNicolas ThomeMatthieu Cord

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 rotations... (read more)

PDF Abstract