3D Computer Vision and its Evolution, seminar by Andrea Tagliasacchi
On 25 September 2024 Andrea Tagliasacchi gave an invited seminar on 3D Computer Vision and its evolution: from depth sensor to novel view synthesis, at the “Enzo Ferrari” Department of Engineering (Room P2.3, Building MO25, Via Vivarelli 10, Modena).
Abstract
Over the last decade, computer vision has undergone a remarkable transformation, with many difficult problems now considered solved. However, much of this progress is often confined to 2D images and videos, which only provide a superficial understanding of the underlying 3D structure. Achieving a comprehensive understanding of 3D scenes remains largely an unsolved challenge. Solving this problem is crucial as computer vision shifts from passive tasks, like search and surveillance, to more active applications that require 3D modeling, such as those that drive the decision-making processes of embodied autonomous systems interacting with the 3D environment. In this talk, I will present my research journey through these areas, beginning with real-time processing techniques for Kinect-style sensors in computer graphics, leading to the development of neural 3D representations and their unsupervised training through novel-view synthesis objectives.
Speaker
Andrea Tagliasacchi is an associate professor at Simon Fraser University (Vancouver, Canada), where he holds the Visual Computing Research Chair, and a part-time staff research scientist at Google DeepMind (Toronto). His research focuses on 3D visual perception, at the intersection of computer vision, computer graphics and machine learning. He received the 2015 SGP best paper award, the 2020 CVPR best student paper award and a 2024 CVPR best paper honorable mention.