Meta AR/VR Job | Research Engineer Intern, Computer Vision/Deep Learning (PhD)
Job（岗位）: Research Engineer Intern, Computer Vision/Deep Learning (PhD)
Type（岗位类型）: Computer Vision | Engineering, Research
Citys（岗位城市）: Redmond, WA | Burlingame, CA
Date（发布日期）: 2022-1-7
Summary（岗位介绍）
The Facebook Reality Labs team at Facebook is helping more people around the world come together and connect through world-class Augmented, Mixed and Virtual Reality hardware and software. With global departments dedicated to AR/VR research, computer vision, haptics, social interaction, and more, we are committed to driving the state-of-the-art forward through relentless innovation. AR and VR potential to change the world is immense — and we’re just getting started.
Our team explores, develops, and delivers cutting-edge scene understanding technologies that serve as the foundation of current and future Facebook Reality Labs products. Planar surfaces serve as the basic building blocks for many scene understanding tasks. For this internship project, we will extend our existing single-view plane reconstruction approaches to better utilize temporary image sequences. Our new approach should be able to improve plane reconstruction accuracy given video sequences.
Qualifications（岗位要求）
Currently has, or is in the process of obtaining, a PhD degree in the field of Computer Vision.
Knowledge in one or more of the following research fields: Scene/Semantic Understanding, Multi-View Geometry.
Strong track record with significant publications in top computer vision conferences (e.g., CVPR, ICCV, ECCV, ICLR, etc.) or journals.
Experience with Python and PyTorch.
Excellent interpersonal skills, cross-group and cross-culture collaboration.
Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment.
Description（岗位职责）
Research, develop, and implement temporary plane reconstruction techniques.
Understand our existing pipeline and implement new modules to enable temporal plane reconstruction.
Communication of research project agenda, projects and results.
Additional Requirements（额外要求）
Experience in applying machine learning / deep learning in the multi-view geometry domain (e.g. Stereo, Depth Estimation, Visual Localization)
Demonstrated software engineer experience (via an internship, work experience, coding competitions, etc)
High levels of creativity and quick problem solving capabilities.
Intent to return to degree-program after the completion of the internship.
