3D Perception Lab

The 3D Perception Lab at the University of Alicante is a group of researchers interested in the intersection of machine learning and computer vision. Our research mission focuses on various aspects of perception often related with mobile robotics in which we exploit 3D data as the main source of information. Some of our research lines include object recognition, semantic segmentation, rigid and non-ridig registration, visual localization and mapping, behavior analysis, and depth estimation. Apart from those general lines we are also highly interested in making those solutions run efficiently by leveraging GPU acceleration using CUDA. Aside from 3D data as our backbone, we are also tied together by our shared vision in the great potential of artificial intelligence, mainly deep learning, which we try to apply and push its limits in every project we work on.

Research Lines

Our main research lines are Machine Learning (Deep Learning specifically), 3D Computer Vision, and GPU Computing. Although our research usually focus on the intersection of those three fields, we are also open to applying our knowledge to cross-disciplinary problems that can be solved by applying artificial intelligence or computer vision techniques. We are also work on the acceleration of algorithms outside that scope that might benefit from a parallel/GPU implementation.

Deep Learning

Artificial intelligence applied to computer vision and robotics (semantic segmentation, depth estimation, scene understanding, object recognition, localization and maping).

3D Computer Vision

Traditional computer vision methods and new challenges for 3D data (rigid registration, non-rigid registration, reconstruction).

GPU Computing

Acceleration of computer vision methods and artificial intelligence pipelines for real-time execution and maximum efficiency.

Selected Publications

2018

Martinez-Gonzalez, Pablo and Oprea, Sergiu and Garcia-Garcia, Alberto and Jover-Alvarez, Alvaro and Orts-Escolano, Sergio and Garcia-Rodriguez, Jose. UnrealROX: An eXtremely Photorealistic Virtual Reality Environment for Robotics Simulations and Synthetic Data Generation. ArXiv e-prints (2018).
[ BibTeX ] [ URL ]

@article{Martinez-Gonzalez2018,
  title = {{UnrealROX}: An eXtremely Photorealistic Virtual Reality Environment for Robotics Simulations and Synthetic Data Generation},
  author = {Martinez-Gonzalez, Pablo and Oprea, Sergiu and Garcia-Garcia, Alberto and Jover-Alvarez, Alvaro and Orts-Escolano, Sergio and Garcia-Rodriguez, Jose},
  journal = {ArXiv e-prints},
  eprint = {1810.06936},
  year = {2018},
  url = {https://arxiv.org/abs/1810.06936}
}

Garcia-Garcia, Alberto and Orts-Escolano, Sergio and Oprea, Sergiu and Villena-Martinez, Victor and Martinez-Gonzalez, Pablo and Garcia-Rodriguez, Jose. A Review on Deep Learning Techniques Applied to Semantic Segmentation. Applied Soft Computing (2018).
[ BibTeX ] [ URL ]

@article{Garcia-Garcia2018,
  author = {Garcia-Garcia, Alberto and Orts-Escolano, Sergio and Oprea, Sergiu and Villena-Martinez, Victor and Martinez-Gonzalez, Pablo and Garcia-Rodriguez, Jose},
  title = {A Review on Deep Learning Techniques Applied to Semantic Segmentation},
  journal = {Applied Soft Computing},
  year = {2018},
  volume = {abs/1704.06857},
  bibsource = {dblp computer science bibliography, http://dblp.org},
  biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/Garcia-GarciaOO17},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  impact_factor_5year = {3.811},
  impact_factor_year = {3.541},
  position = {21/133},
  quartile = {Q1},
  show_website = {True},
  timestamp = {Tue, 02 May 2017 14:18:23 +0200},
  url = {http://arxiv.org/abs/1704.06857}
}

2017

Oprea, Sergiu and Garcia-Garcia, Alberto and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Cazorla, Miguel. A Recurrent Neural Network based Schaeffer Gesture Recognition System. 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, Alaska, May 14-19, 2017 (2017).
[ BibTeX ] [ URL ]

@inproceedings{Oprea2017b,
  author = {Oprea, Sergiu and Garcia-Garcia, Alberto and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Cazorla, Miguel},
  title = {A Recurrent Neural Network based Schaeffer Gesture Recognition System},
  booktitle = {2017 International Joint Conference on Neural Networks, {IJCNN} 2017, Anchorage, Alaska, May 14-19, 2017},
  year = {2017},
  crossref = {DBLP:conf/ijcnn/2017},
  ggs_class = {2},
  ggs_rating = {A-},
  show_website = {True},
  url = {https://ieeexplore.ieee.org/document/7965885/}
}

Gomez-Donoso, Francisco and Garcia-Garcia, Alberto and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Cazorla, Miguel. LonchaNet: A Sliced-based CNN Architecture for Real-time 3D Object Recognition. 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, Alaska, May 14-19, 2017 (2017).
[ BibTeX ] [ URL ]

@inproceedings{Gomez-Donoso2017b,
  author = {Gomez-Donoso, Francisco and Garcia-Garcia, Alberto and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Cazorla, Miguel},
  title = {LonchaNet: A Sliced-based CNN Architecture for Real-time 3D Object Recognition},
  booktitle = {2017 International Joint Conference on Neural Networks, {IJCNN} 2017, Anchorage, Alaska, May 14-19, 2017},
  year = {2017},
  crossref = {DBLP:conf/ijcnn/2017},
  ggs_class = {2},
  ggs_rating = {A-},
  show_website = {True},
  url = {https://ieeexplore.ieee.org/document/7965883/}
}

Castro-Vargas, John Alejandro and Garcia-Garcia, Alberto and Oprea, Sergiu and Orts-Escolano, Sergio and Garcia-Rodriguez, Jose. Detecting and Manipulating Objects with a Social Robot: An Ambient Assisted Living Approach. ROBOT 2017: Third Iberian Robotics Conference - Volume 1, Seville, Spain, November 22-24, 2017 (2017). DOI: 10.1007/978-3-319-70833-1_50
[ BibTeX ] [ URL ]

@inproceedings{Castro-Vargas2017,
  author = {Castro-Vargas, John Alejandro and Garcia-Garcia, Alberto and Oprea, Sergiu and Orts-Escolano, Sergio and Garcia-Rodriguez, Jose},
  title = {Detecting and Manipulating Objects with a Social Robot: An Ambient Assisted Living Approach},
  booktitle = {{ROBOT} 2017: Third Iberian Robotics Conference - Volume 1, Seville, Spain, November 22-24, 2017},
  year = {2017},
  pages = {613--624},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/bib/conf/robot/Castro-VargasGO17},
  crossref = {DBLP:conf/robot/2017-1},
  doi = {10.1007/978-3-319-70833-1_50},
  timestamp = {Thu, 30 Nov 2017 20:21:16 +0100},
  url = {https://doi.org/10.1007/978-3-319-70833-1_50}
}

Garcia-Garcia, Alberto and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Oprea, Sergiu and Gomez-Donoso, Francisco and Cazorla, Miguel. A study of the effect of noise and occlusion on the accuracy of convolutional neural networks applied to 3D object recognition. Computer Vision and Image Understanding (2017). DOI: 10.1016/j.cviu.2017.06.006
[ BibTeX ] [ URL ]

@article{Garcia-Garcia2017,
  author = {Garcia-Garcia, Alberto and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Oprea, Sergiu and Gomez-Donoso, Francisco and Cazorla, Miguel},
  title = {A study of the effect of noise and occlusion on the accuracy of convolutional neural networks applied to 3D object recognition},
  journal = {Computer Vision and Image Understanding},
  year = {2017},
  volume = {164},
  pages = {124--134},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/bib/journals/cviu/Garcia-GarciaRO17},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  doi = {10.1016/j.cviu.2017.06.006},
  impact_factor_5year = {2.595},
  impact_factor_year = {2.498},
  position = {41/133},
  quartile = {Q2},
  show_website = {True},
  timestamp = {Wed, 20 Dec 2017 14:42:07 +0100},
  url = {https://doi.org/10.1016/j.cviu.2017.06.006}
}

Gomez-Donoso, Francisco and Orts-Escolano, Sergio and Garcia-Garcia, Alberto and Garcia-Rodriguez, Jose and Castro-Vargas, John Alejandro and Ovidiu-Oprea, Sergiu and Cazorla, Miguel. A robotic platform for customized and interactive rehabilitation of persons with disabilities. Pattern Recognition Letters (2017). DOI: 10.1016/j.patrec.2017.05.027
[ BibTeX ] [ URL ]

@article{Gomez-Donoso2017,
  author = {Gomez-Donoso, Francisco and Orts-Escolano, Sergio and Garcia-Garcia, Alberto and Garcia-Rodriguez, Jose and Castro-Vargas, John Alejandro and Ovidiu-Oprea, Sergiu and Cazorla, Miguel},
  title = {A robotic platform for customized and interactive rehabilitation of persons with disabilities},
  journal = {Pattern Recognition Letters},
  year = {2017},
  volume = {99},
  pages = {105--113},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/bib/journals/prl/Gomez-DonosoOGR17},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  doi = {10.1016/j.patrec.2017.05.027},
  impact_factor_5year = {2.164},
  impact_factor_year = {1.995},
  position = {58/133},
  quartile = {Q2},
  show_website = {True},
  timestamp = {Thu, 26 Oct 2017 16:15:37 +0200},
  url = {https://doi.org/10.1016/j.patrec.2017.05.027}
}

Cano, Gaspar and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Garcia-Garcia, Alberto and Peña-Garcia, Jorge and Perez-Garrido, Alfonso and Perez-Sanchez, Horacio. Predicción de solubilidad de fármacos usando máquinas de soporte vectorial sobre unidades de procesamiento gráfico. Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería (2017). DOI: https://doi.org/10.1016/j.rimni.2015.12.001
[ BibTeX ] [ URL ]

@article{Cano2017,
  author = {Cano, Gaspar and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Garcia-Garcia, Alberto and Peña-Garcia, Jorge and Perez-Garrido, Alfonso and Perez-Sanchez, Horacio},
  title = {Predicción de solubilidad de fármacos usando máquinas de soporte vectorial sobre unidades de procesamiento gráfico},
  journal = {Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería},
  year = {2017},
  volume = {33},
  number = {1},
  pages = {97 - 102},
  issn = {0213-1315},
  category = {ENGINEERING, MULTIDISCIPLINARY},
  doi = {https://doi.org/10.1016/j.rimni.2015.12.001},
  impact_factor_5year = {0.345},
  impact_factor_year = {0.431},
  keywords = {Máquinas de Soporte Vectorial, Unidades de Procesamiento Gráfico, Bioinformática, Biología Computacional, Support Vector Machines, Graphic Processor Units, Bioinformatics, Computational Biology},
  position = {74/85},
  quartile = {Q4},
  url = {http://www.sciencedirect.com/science/article/pii/S0213131516000067}
}

Oprea, Sergiu and Garcia‐Garcia, Alberto and Orts‐Escolano, Sergio and Villena‐Martinez, Victor and Castro‐Vargas, John. A long short-term memory based Schaeffer gesture recognition system. Expert Systems (2017). DOI: 10.1111/exsy.12247
[ BibTeX ] [ URL ]

@article{Oprea2017,
  author = {Oprea, Sergiu and Garcia‐Garcia, Alberto and Orts‐Escolano, Sergio and Villena‐Martinez, Victor and Castro‐Vargas, John},
  title = {A long short-term memory based Schaeffer gesture recognition system},
  journal = {Expert Systems},
  year = {2017},
  volume = {0},
  number = {0},
  pages = {e12247},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  doi = {10.1111/exsy.12247},
  impact_factor_5year = {1.180},
  impact_factor_year = {1.188},
  position = {91/133},
  quartile = {Q3},
  show_website = {True},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/exsy.12247}
}

2016

Garcia-Garcia, Alberto and Gomez-Donoso, Francisco and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Cazorla, Miguel and Lopez, Jorge Azorin. PointNet: A 3D Convolutional Neural Network for real-time object class recognition. 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, BC, Canada, July 24-29, 2016 (2016). DOI: 10.1109/IJCNN.2016.7727386
[ BibTeX ] [ URL ]

@inproceedings{Garcia-Garcia2016c,
  author = {Garcia-Garcia, Alberto and Gomez-Donoso, Francisco and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Cazorla, Miguel and Lopez, Jorge Azorin},
  title = {PointNet: A 3D Convolutional Neural Network for real-time object class recognition},
  booktitle = {2016 International Joint Conference on Neural Networks, {IJCNN} 2016, Vancouver, BC, Canada, July 24-29, 2016},
  year = {2016},
  pages = {1578--1584},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/bib/conf/ijcnn/Garcia-GarciaGR16},
  crossref = {DBLP:conf/ijcnn/2016},
  doi = {10.1109/IJCNN.2016.7727386},
  ggs_class = {2},
  ggs_rating = {A-},
  show_website = {True},
  timestamp = {Fri, 26 May 2017 00:50:14 +0200},
  url = {https://doi.org/10.1109/IJCNN.2016.7727386}
}

Garcia-Garcia, Alberto and Orts-Escolano, Sergio and Oprea, Sergiu and Garcia-Rodriguez, Jose and Azorin-Lopez, Jorge and Saval-Calvo, Marcelo and Cazorla, Miguel. Multi-sensor 3D object dataset for object recognition with full pose estimation. Neural Computing and Applications (2016). DOI: 10.1007/s00521-016-2224-9
[ BibTeX ] [ URL ]

@article{Garcia-Garcia2016b,
  author = {Garcia-Garcia, Alberto and Orts-Escolano, Sergio and Oprea, Sergiu and Garcia-Rodriguez, Jose and Azorin-Lopez, Jorge and Saval-Calvo, Marcelo and Cazorla, Miguel},
  title = {Multi-sensor 3D object dataset for object recognition with full pose estimation},
  journal = {Neural Computing and Applications},
  year = {2016},
  volume = {28},
  pages = {941--952},
  issn = {1433-3058},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  doi = {10.1007/s00521-016-2224-9},
  impact_factor_5year = {2.012},
  impact_factor_year = {2.505},
  position = {40/133},
  quartile = {Q2},
  show_website = {True},
  url = {http://dx.doi.org/10.1007/s00521-016-2224-9}
}

Saval-Calvo, Marcelo and Azorin-Lopez, Jorge and Fuster-Guillo, Andres and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Garcia-Garcia, Alberto. Evaluation of sampling method effects in 3D non-rigid registration. Neural Computing and Applications (2016). DOI: 10.1007/s00521-016-2258-z
[ BibTeX ] [ URL ]

@article{Saval-Calvo2016,
  author = {Saval-Calvo, Marcelo and Azorin-Lopez, Jorge and Fuster-Guillo, Andres and Garcia-Rodriguez, Jose and Orts-Escolano, Sergio and Garcia-Garcia, Alberto},
  title = {Evaluation of sampling method effects in 3D non-rigid registration},
  journal = {Neural Computing and Applications},
  year = {2016},
  volume = {28},
  pages = {953--967},
  issn = {1433-3058},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  doi = {10.1007/s00521-016-2258-z},
  impact_factor_5year = {2.012},
  impact_factor_year = {2.505},
  position = {40/133},
  quartile = {Q2},
  show_website = {True},
  url = {http://dx.doi.org/10.1007/s00521-016-2258-z}
}

Orts-Escolano, Sergio and Garcia-Rodriguez, Jose and Cazorla, Miguel and Morell, Vicente and Azorin-Lopez, Jorge and Saval-Calvo, Marcelo and Garcia-Garcia, Alberto and Villena-Martinez, Victor. Bioinspired point cloud representation: 3D object tracking. Neural Computing and Applications (2016). DOI: 10.1007/s00521-016-2585-0
[ BibTeX ] [ URL ]

@article{Orts-Escolano2016,
  author = {Orts-Escolano, Sergio and Garcia-Rodriguez, Jose and Cazorla, Miguel and Morell, Vicente and Azorin-Lopez, Jorge and Saval-Calvo, Marcelo and Garcia-Garcia, Alberto and Villena-Martinez, Victor},
  title = {Bioinspired point cloud representation: 3D object tracking},
  journal = {Neural Computing and Applications},
  year = {2016},
  volume = {29},
  pages = {663--672},
  month = sep,
  issn = {1433-3058},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  day = {16},
  doi = {10.1007/s00521-016-2585-0},
  impact_factor_5year = {2.012},
  impact_factor_year = {2.505},
  position = {40/133},
  quartile = {Q2},
  url = {https://doi.org/10.1007/s00521-016-2585-0}
}

Garcia-Garcia, Alberto and Orts-Escolano, Sergio and Garcia-Rodriguez, Jose and Cazorla, Miguel. Interactive 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors. Journal of Real-Time Image Processing (2016). DOI: 10.1007/s11554-016-0607-x
[ BibTeX ] [ URL ]

@article{Garcia-Garcia2016,
  author = {Garcia-Garcia, Alberto and Orts-Escolano, Sergio and Garcia-Rodriguez, Jose and Cazorla, Miguel},
  title = {Interactive 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors},
  journal = {Journal of Real-Time Image Processing},
  year = {2016},
  volume = {14},
  pages = {585--604},
  month = jun,
  issn = {1861-8219},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  day = {04},
  doi = {10.1007/s11554-016-0607-x},
  impact_factor_5year = {1.797},
  impact_factor_year = {2.010},
  position = {54/133},
  quartile = {Q2},
  show_website = {True},
  url = {https://doi.org/10.1007/s11554-016-0607-x}
}

2015

Orts-Escolano, Sergio and Rodriguez, Jose Garcia and Morell, Vicente and Cazorla, Miguel and Garcia-Garcia, Alberto and Oprea, Sergiu. Optimized Representation of 3D Sequences Using Neural Networks. Bioinspired Computation in Artificial Systems - International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2015, Elche, Spain, June 1-5, 2015, Proceedings, Part II (2015). DOI: 10.1007/978-3-319-18833-1_27
[ BibTeX ] [ URL ]

@inproceedings{Orts-Escolano2015b,
  author = {Orts-Escolano, Sergio and Rodriguez, Jose Garcia and Morell, Vicente and Cazorla, Miguel and Garcia-Garcia, Alberto and Oprea, Sergiu},
  title = {Optimized Representation of 3D Sequences Using Neural Networks},
  booktitle = {Bioinspired Computation in Artificial Systems - International Work-Conference on the Interplay Between Natural and Artificial Computation, {IWINAC} 2015, Elche, Spain, June 1-5, 2015, Proceedings, Part {II}},
  year = {2015},
  pages = {251--260},
  bibsource = {dblp computer science bibliography, http://dblp.org},
  biburl = {http://dblp.uni-trier.de/rec/bib/conf/iwinac/Orts-EscolanoRM15},
  crossref = {DBLP:conf/iwinac/2015-2},
  doi = {10.1007/978-3-319-18833-1_27},
  timestamp = {Tue, 26 May 2015 14:19:32 +0200},
  show_website = {True},
  url = {http://dx.doi.org/10.1007/978-3-319-18833-1_27}
}

Orts-Escolano, Sergio and Garcia-Rodriguez, Jose and Morell, Vicente and Cazorla, Miguel and Serra-Perez, Jose Antonio and Garcia-Garcia, Alberto. 3D Surface Reconstruction of Noisy Point Clouds Using Growing Neural Gas: 3D Object/Scene Reconstruction. Neural Processing Letters (2015). DOI: 10.1007/s11063-015-9421-x
[ BibTeX ] [ URL ]

@article{Orts-Escolano2015,
  author = {Orts-Escolano, Sergio and Garcia-Rodriguez, Jose and Morell, Vicente and Cazorla, Miguel and Serra-Perez, Jose Antonio and Garcia-Garcia, Alberto},
  title = {3D Surface Reconstruction of Noisy Point Clouds Using Growing Neural Gas: 3D Object/Scene Reconstruction},
  journal = {Neural Processing Letters},
  year = {2015},
  volume = {43},
  pages = {401--423},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  doi = {10.1007/s11063-015-9421-x},
  impact_factor_5year = {1.503},
  impact_factor_year = {1.747},
  position = {49/130},
  quartile = {Q2},
  show_website = {True},
  url = {http://dx.doi.org/10.1007/s11063-015-9421-x}
}

2014

Orts-Escolano, Sergio and Garcia-Rodriguez, Jose and Serra-Perez, Jose Antonio and Jimeno-Morenilla, Antonio and Garcia-Garcia, Alberto and Morell, Vicente and Cazorla, Miguel. 3D model reconstruction using neural gas accelerated on GPU. Applied Soft Computing (2014). DOI: 10.1016/j.asoc.2015.03.042
[ BibTeX ] [ URL ]

@article{Orts-Escolano2014,
  author = {Orts-Escolano, Sergio and Garcia-Rodriguez, Jose and Serra-Perez, Jose Antonio and Jimeno-Morenilla, Antonio and Garcia-Garcia, Alberto and Morell, Vicente and Cazorla, Miguel},
  title = {3D model reconstruction using neural gas accelerated on GPU},
  journal = {Applied Soft Computing},
  year = {2014},
  volume = {32},
  pages = {87--100},
  category = {COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE},
  doi = {10.1016/j.asoc.2015.03.042},
  impact_factor_5year = {3.222},
  impact_factor_year = {2.810},
  position = {17/123},
  quartile = {Q1},
  show_website = {True},
  url = {http://dx.doi.org/10.1016/j.asoc.2015.03.042}
}

Projects

Our team develops its research lines through various funded projects related to computer vision and robotics. Take a look at our cutting-edge research.

Tech4Diet

This project is aimed at improvement the obesity treatment, from a multidisciplinary perspective by using state of the art technology of 3D modeling or virtual reality to study currently unsolved problems related to the adherence treatment. This opens new opportunities to study dietary and nutritional aspects and provides new challenges in technological research.

Tech4Diet

COMBAHO

The main scientific objective of this project is to promote the health and well-being of society through the design, development and evaluation of an assistant for people with acquired or dependent brain damage to help them face the challenges posed by their illness in their full social integration in both indoor and outdoor environments.

COMBAHO

SIRMAVED

SIRMAVED is a multisensor system for rehabilitation and interaction of people with motor and cognitive disabilities. The system enables to perform different therapies using multiple modes of interaction (pose, body and hands gestures, voice, touch and gaze position) depending on the type and degree of disability. Through a training process, the system can be customized enabling the definition of patients’ own gestures for each sensor. The system is integrated with a range of applications for rehabilitation.

SIRMAVED

Research Highlights

UnrealROX

UnrealROX is an environment built over Unreal Engine 4 which aims to reduce the reality gap when training deep learning architectures by leveraging hyperrealistic indoor scenes that are explored by robot agents which also interact with objects in a visually realistic manner in that simulated world.

UnrealROX

Virtual Reality

Interactive 3D Object Recognition

In this work, we propose the implementation of a 3D object recognition system which will be optimized to operate under demanding time constraints. The system must be robust so that objects can be recognized properly in poor light conditions and cluttered scenes with significant levels of occlusion.

Deep Learning

3D Computer Vision

GPU Computing

2018

2017

2016

2015

2014

Tech4Diet

Tech4Diet

COMBAHO

COMBAHO

SIRMAVED

SIRMAVED

UnrealROX

UnrealROX

Virtual Reality

Interactive 3D Object Recognition

Interactive 3D Object Recognition

Object Recognition

Jose Garcia-Rodriguez

Full Professor

Miguel Cazorla-Quevedo

Full Professor

Jorge Azorin-Lopez

Full Professor

Andres Fuster-Guillo

Full Professor

Sergio Orts-Escolano

Assistant Professor

Marcelo Saval-Calvo

Assistant Professor

Alberto Garcia-Garcia

PhD Student | 3D Deep Learning

Sergiu Ovidiu Oprea

PhD Student | Predictive Learning

Zuria Bauer Hartwig

PhD Student | Deep Depth Estimation

Victor Villena-Martinez

PhD Student | Non-rigid Reconstruction

Francisco Gomez-Donoso

PhD Student | Object Recognition

Pablo Martinez-Gonzalez

PhD Student | Deep Online Learning

John Castro-Vargas

PhD Student | Deep Reinforcement Learning

Groot

Mascot

Andres Carpena-Latour

MsC Automation and Robotics | Deep Reinforcement Learning

Alexei Jilinsky

BsC Multimedia Engineering | Virtual Reality

Adrian Frances-Lillo

BsC Multimedia Engineering | Reinforcement Learning

Pablo Lopez-Iborra

BsC Multimedia Engineering | Virtual Reality

Placido Lopez-Avila

BsC Computer Science | Deep Action Recognition

Jordi Amoros

BsC Computer Science | Deep Learning

Carlos Perello-Camacho

BsC Computer Science | Deep Natural Language Processing