Journey of Leveraging Multiple Cameras in Computer Vision
COM1 Level 2
Cerebro@SoC, COM1-02-05
Abstract :
Since 1997, when Professor Hideo Saito first began researching methods for reconstructing the 3D shape of a scene from multi-view videos captured by 50 cameras and generating free-viewpoint video, he has been deeply engaged in the challenges and possibilities of multi-camera computer vision. Over the years, his research has spanned various topics, including free-viewpoint video generation, camera calibration for multi-view systems, camera tracking and SLAM, and AR/MR applications utilizing free-viewpoint image synthesis. More recently, he has explored applications of these technologies in surgical video recording.
Through these endeavors, he has had the opportunity to collaborate with researchers from diverse fields and contribute to advancing multi-camera vision technologies. In this talk, he will introduce key projects from his research and discuss future directions for leveraging multi-camera systems in novel applications.
Bio:
Hideo Saito received his Ph.D. in Electrical Engineering from Keio University, Japan, in 1992. Since then, he has been a faculty member in the Faculty of Science and Technology at Keio University, where he became a Full Professor in 2006. From 1997 to 1999, he was a Visiting Researcher at the Robotics Institute, Carnegie Mellon University, where he contributed to the Virtualized Reality Project. His research focuses on computer vision and pattern recognition, with applications in augmented reality, virtual reality, and human-robot interaction.
Dr. Saito has played significant roles in the academic community, serving as the Program Chair of ACCV 2014, General Chair of ISMAR 2015, Program Chair of ISMAR 2016, and Scientific Program Chair of Euro VR 2020. He is a Fellow of the Institute of Electronics, Information and Communication Engineers (IEICE) and the Virtual Reality Society of Japan (VRSJ).
He is currently serving as the President of the Information and Systems Society of IEICE and the next President of the Institute of Image Information and Television Engineers. His achievements include multiple awards, most notably the Best Journal Paper Award at ISMAR 2023.