Omnidirectional Computer Vision

in research and industry

in conjunction with IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, WA

Monday, June 15, 2020

Accepted papers will be published in IEEE Xplore!


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. This full day workshop has twelve invited speakers from both academia and industry.

The full set of keynote talks and poster presentations can be found on this YouTube playlist or on the individual event pages on our Program page.

Keynote Speakers

For detailed speaker bios, please see the Keynote Speakers page


Davide Scaramuzza

Professor, University of Zurich

Jean-François Lalonde

Associate Professor, Université Laval

Kristen Grauman

Professor, University of Texas at Austin

Daniel Cremers

Professor, Technical University of Munich

Matthias Nießner

Professor, Technical University of Munich

Taco Cohen

Research Scientist, Qualcomm

Tomas Pajdla

Associate Professor, Czech Technical University in Prague


Ricoh Company

Hirochika Fujiki, Engineer


Rajat Aggarwal, CEO


Ganesh Sistu, Computer Vision and Deep Learning Expert for Automated Driving

Wormpex AI

Gang Hua, VP and Chief Scientist

Zillow Group

Sing Bing Kang, Distinguished Scientist

Keynote Topics

For more details, please see the Program page

  • "Event Cameras: Opportunities and the Road Ahead" (Davide Scaramuzza)
  • "Leveraging omnidirectional images to learn how to estimate lighting" (Jean-François Lalonde)
  • "Seeing sounds and space" (Kristen Grauman)
  • "Deep Direct Visual SLAM" (Daniel Cremers)
  • "From 3D Scene Understanding to 3D Self-Supervision" (Matthias Nießner)
  • "OmniDirectional CNNs" (Taco Cohen)
  • "Camera Pose Computation with Rolling Shutter" (Tomas Pajdla)
  • "Watch Ricoh THETA and Applications of 360 Imaging" (Hirochika Fujiki, Ricoh)
  • "Making Single Sensor Omnidirectional Stereo Cameras a Reality" (Rajat Aggarwal, DreamVu)
  • "Fisheye Camera Perception for Automated Driving" (Ganesh Sistu, Valeo)
  • "Omni-vision Applied Research at Zillow" (Sing Bing Kang, Zillow)
  • "From Digitization, Decision to Execution: The Role of 360 Vision in Brick and Mortar Convenience Retail Operation" (Gang Hua, Wormpex AI)

Points of Contact

Marc Eder (

Senthil Yogamani (

Ciarán Hughes (

Stefan Milz (Website)(