March 30, 2023 Thursday
Abstract:
Omni cameras, also called 360 cameras have become increasingly popular as a 360-degree image provides holistic sensing of a scene with a much wider field of view (FoV)- 360×180 than the 2D RGB cameras. As 360 cameras can capture every angle of a scene, creating immersive and interactive content, there is a growing demand for utilizing such visual content for intelligent systems, such as virtual reality (VR) and autonomous driving. In this talk, I will first talk about the basic principle of 360 cameras and the spherical image representation types. Then, I will talk about how to bring deep learning to 360 camera-based vision. Lastly, I will share some of our recent research works typically targeted at scene understanding and interactive 3D model synthesis for VR and autonomous driving.
Speaker Bio:
Dr. Lin WANG
Assistant Professor, AI Thrust, INFH, HKUST(GZ)
Dr. WANG Lin (Addison) is an Assistant Professor in the Artificial Intelligence (AI) Thrust of Information Hub (GZ Campus) and an Affiliate Assistant Professor in the Department of Computer Science and Engineering (CWB Campus), HKUST. He got his Ph.D. Degree (with Highest Ph.D. Research Award) from Korea Advanced Institute of Science and Technology (KAIST), majoring in AI-driven computer and robotic vision. Dr. WANG had study and research experience in three departments, which makes him interested in the inter-disciplinary research problems aiming to integrate computer vision, graphics and HCI and further explore the combined potential for intelligent systems, such as autonomous driving and Metaverse. He had published many first-authored top-tier conference and journal works in computer vision and robotics fields, such as IEEE TPAMI, CVPR, etc.