27 citations · 81 across the 22 of their papers we have counts for
5 papers · 1 filter
Defining an action of SO(d)-rotations on images generated by projections of d-dimensional objects: Applications to pose inference with Geometric VAEs
Nicolas Legendre, Khanh Dao Duc, Nina Miolane
Recent advances in variational autoencoders (VAEs) have enabled learning latent manifolds as compact Lie groups, such as . Since this approach assumes that data lies on a su…
CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Images
Axel Levy, Frédéric Poitevin, Julien Martel +6
Cryo-electron microscopy (cryo-EM) has become a tool of fundamental importance in structural biology, helping us understand the basic building blocks of life. The algorithmic chall…
Riemannian Functional Map Synchronization for Probabilistic Partial Correspondence in Shape Networks
Faria Huq, Adrish Dey, Sahra Yusuf +3
We consider the problem of graph-matching on a network of 3D shapes with uncertainty quantification. We assume that the pairwise shape correspondences are efficiently represented a…
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
Benjamin Hou, Nina Miolane, Bishesh Khanal +7
Pose estimation, i.e. predicting a 3D rigid transformation with respect to a fixed co-ordinate frame in, SE(3), is an omnipresent problem in medical image analysis with application…
Template shape estimation: correcting an asymptotic bias
Nina Miolane, Susan Holmes, Xavier Pennec
We use tools from geometric statistics to analyze the usual estimation procedure of a template shape. This applies to shapes from landmarks, curves, surfaces, images etc. We demons…