Prof. Dinesh Manocha (ACM Fellow, IEEE Fellow, AAAI Fellow, AAAS Fellow)
University of Maryland, USA
Biography: Dinesh Manocha is Paul Chrisman-Iribe Chair in Computer Science & ECE and Distinguished University Professor at University of Maryland College Park. His research interests include virtual environments, physically-based modeling, and robotics. His group has developed a number of software packages that are standard and licensed to 60+ commercial vendors. He has published more than 700 papers & supervised 43 PhD dissertations. He is a Fellow of AAAI, AAAS, ACM, and IEEE, member of ACM SIGGRAPH Academy, and Bézier Award from Solid Modeling Association. He received the Distinguished Alumni Award from IIT Delhi the Distinguished Career in Computer Science Award from Washington Academy of Sciences. He was a co-founder of Impulsonic, a developer of physics-based audio simulation technologies, which was acquired by Valve Inc in November 2016. He is also a co-founder of Inception Robotics.
Title: Augmented Intelligence
Abstract: We give an overview of recent developments in terms of developing next generation human-computing interface technologies that combine AI Technologies based on vision, speech and NLP with virtual and augmented reality methods. This includes novel handheld and immersive devices that use multiple sensors to capture the environment and increase the sense of realism. We will describe new methods for generating intelligent virtual avatars and demonstrate their benefits for social VR and 3D Interactions. We will highlight their benefits for virtual try on, digital virtual assistants and computer-aided design.
Prof. Hideo Saito
Keio University, Japan
Biography: HIDEO SAITO received a Ph.D. degree in electrical engineering from Keio University, Japan, in 1992. Since 1992, he has been in the Faculty of Science and Technology, Keio University. From 1997 to 1999, he joined the Virtualized Reality Project at the Robotics Institute, Carnegie Mellon University, as a Visiting Researcher. Since 2006, he has been a Full Professor of Keio University. Since 2020, he is the chair professor of the Department of Information and Computer Science at Keio University. His research interests include computer vision and pattern recognition, and their applications to augmented reality, virtual reality, and human-robotic interaction. His recent activities in academic conferences include being the Program Chair of ACCV 2014, the General Chair of ISMAR 2015, the Program Chair of ISMAR 2016, and the Scientific Program Chair of Euro VR2020. He is a fellow of IEICE (Institute of Electronics, Information and Communication Engineers) and VRSJ (Virtual Reality Society of Japan).
Speech Title: Image Based Rendering by Deep-Learning based Computer Vision
Abstract: Ten years have passed since deep learning was shown to be capable of dramatically improving image recognition performance. In the past decade, various studies have shown that deep learning can innovatively improve conventional image recognition and sensing performance. Image Based Rendering (IBR) for the computational synthesis of images that cannot be captured with generic cameras has also made innovative progress with deep-learning-based computer vision. In this talk, I would like to talk about recent IBR technologies driven by such deep-learning algorithms for visualizing scenes that cannot be captured by ordinary cameras. Deep learning with a huge amount of training data makes what was impossible with the classical techniques possible. I will demonstrate it by showing deep-learning-enhanced estimation of geometric information, such as camera poses, human poses, and 3D structures of environments. Then, I would also show examples of how deep learning can contribute to practical applications of IBR including AR/VR visualizations. I will finally give my expectation for the future of the marriage of such deep learning and computer vision technologies.