46 citations · 98 across the 6 of their papers we have counts for
6 papers
WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks
Javier Cremona, Lucas Uzal, Taihú Pire
In this work we present WGANVO, a Deep Learning based monocular Visual Odometry method. In particular, a neural network is trained to regress a pose estimate from an image pair. Th…
Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images
Marcos Pividori, Guillermo L. Grinblat, Lucas C. Uzal
Generative Adversarial Networks (GAN) have demonstrated impressive results in modeling the distribution of natural images, learning latent representations that capture semantic var…
Exploiting video sequences for unsupervised disentangling in generative adversarial networks
Facundo Tuesca, Lucas C. Uzal
In this work we present an adversarial training algorithm that exploits correlations in video to learn --without supervision-- an image generator model with a disentangled latent s…
Class-Splitting Generative Adversarial Networks
Guillermo L. Grinblat, Lucas C. Uzal, Pablo M. Granitto
Generative Adversarial Networks (GANs) produce systematically better quality samples when class label information is provided., i.e. in the conditional GAN setup. This is still obs…
Optimal reconstruction of dynamical systems: A noise amplification approach
L. C. Uzal, G. L. Grinblat, P. F. Verdes
In this work we propose an objective function to guide the search for a state space reconstruction of a dynamical system from a time series of measurements. This statistics can be…
Predictions of the Maximum Amplitude, Time of Occurrence, and Total Length of Solar Cycle 24
L. C. Uzal, R. D. Piacentini, P. F. Verdes
In this work we predict the maximum amplitude, its time of occurrence, and the total length of Solar Cycle 24 by linear regression to the curvature (second derivative) at the prece…