A5091815561- Generative Adversarial Networks and Image Synthesis
- Robotics and Sensor-Based Localization
- Face recognition and analysis
- Indoor and Outdoor Localization Technologies
- Robotic Path Planning Algorithms
- Target Tracking and Data Fusion in Sensor Networks
- Facial Nerve Paralysis Treatment and Research
- Advanced Vision and Imaging
- Modular Robots and Swarm Intelligence
Meta (Israel)
2019
West Virginia University
2017-2018
A key promise of Virtual Reality (VR) is the possibility remote social interaction that more immersive than any prior telecommunication media. However, existing VR experiences are mediated by inauthentic digital representations user (i.e., stylized avatars). These have limited adoption applications in precisely those cases where immersion most necessary (e.g., professional interactions and intimate conversations). In this work, we present a bidirectional system can animate avatar heads both...
Photorealistic avatars of human faces have come a long way in recent years, yet research along this area is limited by lack publicly available, high-quality datasets covering both, dense multi-view camera captures, and rich facial expressions the captured subjects. In work, we present Multiface, new multi-view, high-resolution face dataset collected from 13 identities at Reality Labs Research for neural rendering. We introduce Mugsy, large scale multi-camera apparatus to capture synchronized...
Abstract This paper presents the design of Cataglyphis, a research rover that won NASA Sample Return Robot Centennial Challenge in 2015. During challenge, Cataglyphis was only robot able to autonomously find, retrieve, and return multiple types samples large natural environment without using Earth‐specific sensors such as GPS magnetic compasses. It navigates through fusion measurements collected from inertial sensors, wheel encoders, nodding Lidar, set ranging radios, camera on panning...