Probabilistic Orientation Estimation with Matrix Fisher Distributions
David Mohlin,Josephine Sullivan,Gu00e9rald Bianchi
This paper focuses on estimating probability distributions over the set of 3D ro-tations (SO(3)) using deep neural networks. Learning to regress models to theset of rotations is inherently difficult due to differences in topology betweenR^N and SO(3). We overcome this issue by using a neural network to out-put the parameters for a matrix Fisher distribution since these parameters arehomeomorphic to R^9 . By using a negative log likelihood loss for this distri-bution we get a loss which is convex with respect to the network outputs. Byoptimizing this loss we improve state-of-the-art on several challenging applica-ble datasets, namely Pascal3D+, ModelNet10-SO(3). Our code is available athttps://github.com/Davmo049/Publicproborientationestimationwithmatrix_fisherdistributions
