Vivek Pradeep

Vivek Pradeep is a CVP and technical fellow in the Applied Sciences Group (ASG) at Microsoft, working on on-device A.I., neural processors, and small language models.  His team is a core contributor to the Windows A.I. stack, all the way from model training to deployment at scale across the devices ecosystem. 

He received his Ph.D. degree from the University of Southern California, Los Angeles in 2011 where he worked on a wearable SLAM system.  Before that, he received his undergraduate degree in electronics and communications engineering from the Indian Institute of Technology, Roorkee.  He has also worked as an intern at the Honda Research Labs in Mountain View CA developing algorithms for the ASIMO robot’s visual navigation system. 

Vivek’s research interests are in the areas of visual odometry, SLAM, 3D reconstruction, camera calibration and machine learning.  At Microsoft, his responsibilities include iterating on efforts related to scenario exploration, sensor and optics design, systems integration and algorithm development for various shipping and explorative vision-based products across the devices family.

• Guidance Network with Staged Learning for Image enhancement

  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021 June, 2021 Pages 836-845

  By Luming Liang, Ilya Zharkov, Faezeh Amjadi, Hamid Vaezi Joze, Vivek Pradeep
• ImagePairs: Realistic Super Resolution Dataset via Beam Splitter Camera Rig

  The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops June, 2020

  By Hamid Vaezi Joze, Ilya Zharkov, Karlton Powell, Carl Ringler, Luming Liang, Andy Roulston, Moshe Lutz, Vivek Pradeep
• DIY Human Action Data Set Generation

  The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops June, 2018

  By Mehran Khodabandeh, Hamid Vaezi Joze, Ilya Zharkov, Vivek Pradeep