Introduction
Our objective is to provide a venue for novel research in omnidirectional computer vision with an eye toward actualizing these ideas for commercial or societal benefit. As omnidirectional cameras become more widespread, we want to bridge the gap between the research and application of omnidirectional vision technologies. Omnidirectional cameras are already widespread in a number of application areas such as automotive, surveillance, photography, simulation and other use-cases that benefit from large field of view. More recently, they have garnered interest for use in virtual and augmented reality. We want to encourage the development of new models that natively operate on omnidirectional imagery as well as close the performance gap between perspective-image and omnidirectional algorithms.
OmniCV 2022 @ CVPR, New Orleans
Sponsors
Motivation
From immersive experiences to autonomous driving to medical imaging and more, we are increasingly seeing that maximizing a camera’s field of view can solve real-world problems. In the past few years, omnidirectional imaging has grown in interest, driven in part by the desire to maximize the amount of content and context encapsulated by a single image. Fisheye cameras installed in modern vehicles and commodity omnidirectional cameras from companies like Ricoh and Insta360 have helped to increase the popularity of this imaging modality and have opened the door for more consumer-facing applications in the automotive, home services and real estate industries, among others. Our workshop seeks to provide a link between the formative research that supports these advances and the realization of commercial products that leverage this technology. We want to encourage the development of new algorithms and applications for this imaging modality that will continue to drive this engine of progress.
Ethical Considerations
Wide field of view and omnidirectional imaging require special privacy considerations as these techniques capture more expansive content than the more common perspective image. Furthermore, the common application of wide field of view imaging to surveillance and its frequent use as an "always-on" sensor for vehicles and augmented reality devices raise questions about how we can leverage the power of this imaging modality while also preserving individual privacy.
We have encouraged our speakers to address these considerations in their keynotes. We also encourage authors to explore topics around the privacy implications of omnidirectional imaging, along with privacy-preserving solutions that are unique to this modality and its applications. We further encourage authors to consider ways to leverage omnidirectional vision to address societal and environmental problems, as well as other important issues, that impact billions of people around the world.
Keynote Speakers
Jan Erik Solem
Chairman at Overture Maps Foundation & Engineering Director, Meta
Jan Erik Solem, a distinguished luminary in the domains of technology and mapping, is set to grace our event as a confirmed speaker. Currently, he holds the prestigious positions of Chairman at Overture Maps Foundation and Engineering Director at Meta, showcasing his exceptional expertise and leadership. With a notable track record as the Director of Maps at Meta and as a co-founder and CEO of Mapillary, Jan Erik has been a trailblazer in leveraging crowdsourced street level imagery for mapping solutions. His past role as a manager at Apple, where he led the computer vision team and conducted pioneering research, further highlights his impactful career. An academic stalwart, Jan Erik's contributions as an associate professor at Lund University underscore his depth of knowledge. Recognized twice as a WEF Technology Pioneer and armed with a plethora of 20+patents, along with being an acclaimed author, Jan Erik Solem is primed to offer profound insights and expertise to our audience.
Prof. Jean-François Lalonde
Full Professor at Université Laval
Jean-François Lalonde, Ph.D., is a distinguished full professor in the Electrical and Computer Engineering Department at Université Laval, where he also serves as the Associate Scientific Director of the Institute of Intelligence and Data (IID). Drawing on a wealth of experience, he previously held a pivotal post-doctoral role at Disney Research, Pittsburgh. Jean-François earned his Ph.D. in Robotics from Carnegie Mellon University in 2011, laying the foundations for an impactful academic journey. His research passions converge at the intersection of computer vision, computer graphics, and machine learning, driving him to explore the unification of physics-based models and data-driven machine learning techniques. Through this pursuit, he aims to comprehend, model, interpret, and recreate the intricate aspects of our visual world. Jean-François boasts an impressive publication record of 70 refereed papers, cited nearly 5,000 times, highlighting the depth and influence of his contributions to academia. Moreover, he actively translates research innovations into the realm of commercial products, showcasing his commitment to bridging academic ingenuity with real-world applications. With nine patents and a notable involvement as a scientific advisor for various high-tech startups, Jean-François Lalonde is primed to bring invaluable insights to our event.
Meysam Sadeghi
Staff Engineer, Qualcomm ADAS
Meysam Sadeghi received his Ph.D. degree from the Singapore University of Technology and Design, Singapore. He was a Postdoctoral Research Fellow with the department of Electrical Engineering, Linköping University, Sweden. Currently he is a staff engineer in Qualcomm's Snapdragon Ride Pre-Dev team. His research interests include end-to-end AD, BEV perception, and online map construction. He is a recipient of the SUTD Best Ph.D. Dissertation Award, the FIRST 2017, the Merlion 2014, among others.
Points of Contact
Sweta Priyadarshi
(swetpriy@qti.qualcomm.com)
Kaavya Rekanar (kaavya.rekanar@ul.ie)
Stefan Milz (website)
(stefan.milz@spleenlab.ai)