Germán Ros

Nvidia (United States) — United States

Computer Science · Physical Sciences

10h-index3.2kcitations29works2.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Video Surveillance and Tracking Methods(8), Advanced Vision and Imaging(8), Advanced Neural Network Applications(7), Domain Adaptation and Few-Shot Learning(6), Advanced Image and Video Retrieval Techniques(5)

Publications29 total

All for one, and one for all: UrbanSyn Dataset, the third Musketeer of synthetic driving scenes
Neurocomputing·2025· 4 cited
Generating Physically Realistic and Directable Human Motions from Multi-modal Inputs
Lecture notes in computer science·2024· 3 citedOpen Access
Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting
2024· 4 cited
Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting
arXiv (Cornell University)·2024Open Access
All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes
arXiv (Cornell University)·2023· 2 citedOpen Access
Panel on Safety, Security, and Reliability of Autonomous Vehicles
2020 Asia-Pacific International Symposium on Advanced Reliability and Maintenance Modeling (APARM)·2020
New Simulation Tools for Training and Testing Automated Vehicles
Lecture notes in mobility·2020· 16 cited
SPIGAN: Privileged Adversarial Learning from Simulation
arXiv (Cornell University)·2018· 27 citedOpen Access
Street-view change detection with deconvolutional networks
Autonomous Robots·2018· 301 cited
A Dataset To Evaluate The Representations Learned By Video Prediction Models
arXiv (Cornell University)·2018· 2 citedOpen Access
A Dataset To Evaluate The Representations Learned By Video Prediction Models
arXiv (Cornell University)·2018· 1 citedOpen Access
CARLA: An Open Urban Driving Simulator
arXiv (Cornell University)·2017· 291 citedOpen Access
Training my car to see using virtual worlds
Image and Vision Computing·2017· 10 cited
Robust object tracking using sparse based representative dictionary learning
2017 International Conference on Computation of Power, Energy Information and Commuincation (ICCPEIC)·2017· 1 cited
From Virtual to Real World Visual Perception Using Domain Adaptation—The DPM as Example
Advances in computer vision and pattern recognition·2017· 7 cited
Semantic Segmentation of Urban Scenes via Domain Adaptation of SYNTHIA
Advances in computer vision and pattern recognition·2017· 6 cited
From Virtual to Real World Visual Perception using Domain Adaptation --\n The DPM as Example
arXiv (Cornell University)·2016Open Access
From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example
arXiv (Cornell University)·2016Open Access
Motion Estimation via Robust Decomposition With Constrained Rank
IEEE Transactions on Intelligent Vehicles·2016· 1 citedOpen Access
Street-View Change Detection with Deconvolutional Networks
2016· 66 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Antonio M. López(13), David Vázquez(7), Simon Stent(5), Jiaolong Xu(4), José Luis Sancho Gómez(4), Julio Guerrero(4), Laura Sellart(3), Pablo F. Alcantarilla(3), Gabriel Villalonga(3), Roberto Arroyo(2), Riccardo Gherardi(2), José M. Alvarez(2), Ángel D. Sappa(2), Daniel Ponsa(2), Benjamin Ummenhofer(2), Sanskar Agrawal(2), Rene Sepulveda(2), Yixing Lao(2), Tianhang Cheng(2), Stephan R. Richter(2)