1.4k citations · 1.6k across the 20 of their papers we have counts for
3 papers · 1 filter
Deep Geometric Prior for Surface Reconstruction
Francis Williams, Teseo Schneider, Claudio Silva +3
The reconstruction of a discrete surface from a point cloud is a fundamental geometry processing problem that has been studied for decades, with many methods developed. We propose…
Unsupervised Feature Learning from Temporal Data
Ross Goroshin, Joan Bruna, Jonathan Tompson +2
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coher…
Geometric Models with Co-occurrence Groups
Joan Bruna, Stéphane Mallat
A geometric model of sparse signal representations is introduced for classes of signals. It is computed by optimizing co-occurrence groups with a maximum likelihood estimate calcul…