5 papers
DuNet: Learning Depth Estimation from Dual-Cameras and Dual-Pixels
Yinda Zhang, Neal Wadhwa, Sergio Orts-Escolano +3
Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges. We present a novel…
A Visually Plausible Grasping System for Object Manipulation and Interaction in Virtual Reality Environments
Sergiu Oprea, Pablo Martinez-Gonzalez, Alberto Garcia-Garcia +3
Interaction in virtual reality (VR) environments is essential to achieve a pleasant and immersive experience. Most of the currently existing VR applications, lack of robust object…
The RobotriX: An eXtremely Photorealistic and Very-Large-Scale Indoor Dataset of Sequences with Robot Trajectories and Interactions
Alberto Garcia-Garcia, Pablo Martinez-Gonzalez, Sergiu Oprea +4
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 Robo…
TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors
Alberto Garcia-Garcia, Brayan Stiven Zapata-Impata, Sergio Orts-Escolano +2
Tactile sensors provide useful contact data during the interaction with an object which can be used to accurately learn to determine the stability of a grasp. Most of the works in…
Large-scale Multiview 3D Hand Pose Dataset
Francisco Gomez-Donoso, Sergio Orts-Escolano, Miguel Cazorla
Accurate hand pose estimation at joint level has several uses on human-robot interaction, user interfacing and virtual reality applications. Yet, it currently is not a solved probl…