2 papers
cs.LG2021
Universal Spectral Adversarial Attacks for Deformable Shapes
Arianna Rampini, Franco Pestarini, Luca Cosmo +2
Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong predictions despite being imperceptible. However, the…
cs.GR2020
Nonlinear Spectral Geometry Processing via the TV Transform
Marco Fumero, Michael Moeller, Emanuele Rodolà
We introduce a novel computational framework for digital geometry processing, based upon the derivation of a nonlinear operator associated to the total variation functional. Such o…