no code implementations • ICLR 2019 • Kuan-Hui Lee, German Ros, Jie Li, Adrien Gaidon
Deep Learning for Computer Vision depends mainly on the source of supervision. Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance.
no code implementations • 22 Aug 2018 • Victor Vaquero, German Ros, Francesc Moreno-Noguer, Antonio M. Lopez, Alberto Sanfeliu
We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning.
no code implementations • 11 Jun 2018 • Michael R. Anderson, Michael Cafarella, German Ros, Thomas F. Wenisch
Modern extraction techniques are based on deep convolutional neural networks (CNNs) and can classify objects within images with astounding accuracy.
1 code implementation • 25 Feb 2018 • Ryan Szeto, Simon Stent, German Ros, Jason J. Corso
We present a parameterized synthetic dataset called Moving Symbols to support the objective study of video prediction networks.
1 code implementation • 10 Nov 2017 • Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, Vladlen Koltun
We introduce CARLA, an open-source simulator for autonomous driving research.
no code implementations • 29 Dec 2016 • Antonio M. Lopez, Jiaolong Xu, Jose L. Gomez, David Vazquez, German Ros
However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA).
no code implementations • CVPR 2016 • German Ros, Laura Sellart, Joanna Materzynska, David Vazquez, Antonio M. Lopez
In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations.
no code implementations • 6 Apr 2016 • German Ros, Simon Stent, Pablo F. Alcantarilla, Tomoki Watanabe
In this work we investigate the problem of road scene semantic segmentation using Deconvolutional Networks (DNs).
1 code implementation • 10 Mar 2015 • German Ros, Julio Guerrero
We address the problem of efficient sparse fixed-rank (S-FR) matrix decomposition, i. e., splitting a corrupted matrix $M$ into an uncorrupted matrix $L$ of rank $r$ and a sparse matrix of outliers $S$.
no code implementations • 22 Oct 2014 • German Ros, Jose Alvarez, Julio Guerrero
To this end we propose the Robust Decomposition with Constrained Rank (RD-CR), a proximal gradient based method that enforces the rank constraints inherent to motion estimation.