Abstract: Computer vision researchers have pushed the limits of performance in perception tasks involving natural images to near saturation. With self-supervised inference driven by recent advancements in generative modeling, it can be debated that the era of large image models is coming to a close, ushering in an era focused on video. However, it’s worth pondering: aren’t the vast majority of videos uploaded to the web essentially 2D representations of a dynamic 3D world? Furthermore, in the context of deploying autonomous systems, wouldn’t it be advantageous for autonomous decisions to take into account all available information sources, rather than relying solely on the video feed from a single agent?  Neural World Models have the capacity to represent geo-located information that can be spatially queried to execute specific tasks. While they extend beyond the traditional concept of mapping, ongoing research is actively exploring how to best represent, capture, convert, and deliver these models to end-users.

Bio: Andrea Tagliasacchi is an associate professor at Simon Fraser University (Vancouver, Canada) where he holds the appointment of “visual computing research chair” within the school of computing science. He is also a part-time (20%) staff research scientist at Google DeepMind (Toronto), as well as an associate professor (status only) in the computer science department at the University of Toronto. Before joining SFU, he spent four wonderful years as a full-time researcher at Google (mentored by Paul Lalonde, Geoffrey Hinton, and David Fleet). Before joining Google, he was an assistant professor at the University of Victoria (2015-2017), where he held the Industrial Research Chair in 3D Sensing (jointly sponsored by Google and Intel). His alma mater include EPFL (postdoc) SFU (PhD, NSERC Alexander Graham Bell fellow) and Politecnico di Milano (MSc, gold medalist). His research focuses on 3D visual perception, which lies at the intersection of computer vision, computer graphics and machine learning – I am hiring graduate students for Sep. 2024.