Sergiu Oprea
YOU?
Author Swipe
View article: Generating Synthetic Hand-Object Contact Maps for Grasping Region Prediction
Generating Synthetic Hand-Object Contact Maps for Grasping Region Prediction Open
View article: UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual 3D Environments
UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual 3D Environments Open
Synthetic data generation has become essential in last years for feeding data-driven algorithms, which surpassed traditional techniques performance in almost every computer vision problem. Gathering and labelling the amount of data needed …
View article: H-GAN: the power of GANs in your Hands
H-GAN: the power of GANs in your Hands Open
We present HandGAN (H-GAN), a cycle-consistent adversarial learning approach implementing multi-scale perceptual discriminators. It is designed to translate synthetic images of hands to the real domain. Synthetic hands provide complete gro…
View article: UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual\n 3D Environments
UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual\n 3D Environments Open
Synthetic data generation has become essential in last years for feeding\ndata-driven algorithms, which surpassed traditional techniques performance in\nalmost every computer vision problem. Gathering and labelling the amount of\ndata need…
View article: Entorno colaborativo de desarrollo de proyectos fin de grado en titulaciones tecnológicas
Entorno colaborativo de desarrollo de proyectos fin de grado en titulaciones tecnológicas Open
La gestión y seguimiento del desarrollo de proyectos o trabajos fin de grado TFG requiere de una gran cantidad de tiempo y suele realizarse de manera individual sin colaboración ni retroalimentación entre alumnos. Debido al desarrollo y pr…
View article: A Review on Deep Learning Techniques for Video Prediction
A Review on Deep Learning Techniques for Video Prediction Open
The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a p…
View article: When Deep Learning Meets Data Alignment: A Review on Deep Registration Networks (DRNs)
When Deep Learning Meets Data Alignment: A Review on Deep Registration Networks (DRNs) Open
This paper reviews recent deep learning-based registration methods. Registration is the process that computes the transformation that aligns datasets, and the accuracy of the result depends on multiple factors. The most significant factors…
View article: UnrealROX: an extremely photorealistic virtual reality environment for robotics simulations and synthetic data generation
UnrealROX: an extremely photorealistic virtual reality environment for robotics simulations and synthetic data generation Open
View article: A visually realistic grasping system for object manipulation and interaction in virtual reality environments
A visually realistic grasping system for object manipulation and interaction in virtual reality environments Open
View article: COMBAHO: A deep learning system for integrating brain injury patients in society
COMBAHO: A deep learning system for integrating brain injury patients in society Open
View article: The RobotriX: An eXtremely Photorealistic and Very-Large-Scale Indoor\n Dataset of Sequences with Robot Trajectories and Interactions
The RobotriX: An eXtremely Photorealistic and Very-Large-Scale Indoor\n Dataset of Sequences with Robot Trajectories and Interactions Open
Enter the RobotriX, an extremely photorealistic indoor dataset designed to\nenable the application of deep learning techniques to a wide variety of robotic\nvision problems. The RobotriX consists of hyperrealistic indoor scenes which\nare …
View article: UnrealROX: An eXtremely Photorealistic Virtual Reality Environment for\n Robotics Simulations and Synthetic Data Generation
UnrealROX: An eXtremely Photorealistic Virtual Reality Environment for\n Robotics Simulations and Synthetic Data Generation Open
Data-driven algorithms have surpassed traditional techniques in almost every\naspect in robotic vision problems. Such algorithms need vast amounts of quality\ndata to be able to work properly after their training process. Gathering and\nan…
View article: The RobotriX: An Extremely Photorealistic and Very-Large-Scale Indoor Dataset of Sequences with Robot Trajectories and Interactions
The RobotriX: An Extremely Photorealistic and Very-Large-Scale Indoor Dataset of Sequences with Robot Trajectories and Interactions Open
Enter the RobotriX, an extremely photorealistic indoor dataset designed to enable the application of deep learning techniques to a wide variety of robotic vision problems. The RobotriX consists of hyperrealistic indoor scenes which are exp…
View article: Classifying Behaviours in Videos with Recurrent Neural Networks
Classifying Behaviours in Videos with Recurrent Neural Networks Open
This article describes how the human activity recognition in videos is a very attractive topic among researchers due to vast possible applications. This article considers the analysis of behaviors and activities in videos obtained with low…
View article: A Review on Deep Learning Techniques Applied to Semantic Segmentation
A Review on Deep Learning Techniques Applied to Semantic Segmentation Open
Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation, …
View article: Multi-sensor 3D object dataset for object recognition with full pose estimation
Multi-sensor 3D object dataset for object recognition with full pose estimation Open