Srikumar Ramalingam is an Associate Professor at the school of computing in the University of Utah since 2017. Previously he worked as a senior principal research scientist for more than 8 years at Mitsubishi Electric Research Laboratories (MERL) in Cambridge. His research interests are in computer vision, machine learning, and robotics. He has contributed broadly to perception and prediction using deep neural networks, theoretical modeling of deep neural networks, submodular optimization algorithms, inference in graphical models, 3D reconstruction, semantic segmentation, visual SLAM, and image-based localization. In particular, he has been developing strong geometrical and learning algorithms in the context of autonomous driving applications.

He has co-authored over 50 peer-reviewed publications and holds over 35 US and international patents. His work has received the INPG best thesis award in 2007, AFRIF best thesis honorable mention given by the french association for pattern recognition, honorable mention award in 2015 Robotics Science and Systems Conference (RSS), and the 2014 R&D 100 award-- awarded to 100 most innovative technology introduced in 2013.

He is fortunate to receive his education in 4 different countries. He received his BE in Computer Science from the college of Engineering, Anna University (Guindy), India. Following his BE in India, he received his MS from UC Santa cruz. His interests in rollerblading and skiing played a role in his choice of schools for studies and job (France, Boston, Utah, etc.). Following his MS in USA, he moved to INRIA Grenoble Rhône-Alpes research lab in France for his Ph.D. at INPG (National Polytechnical Institute of Grenoble). He received a Marie Curie Visitron scholarship, and he pursued his Ph.D. under the guidance of Dr. Peter Sturm . Following his Ph.D. he worked as a postdoc at Oxford Brookes University (and affiliated member in Oxford University) under the guidance of Prof. Philip H.S. Torr.

email / Google Scholar / LinkedIn / Twitter / GitHub

  • I am giving an invited talk in the Workshop IV: Deep Geometric Learning of Big Data and Applications organized by Institute for Pure and Applied Mathematics (IPAM)
  • I co-organized the workshop AutoNUE: Autonomous Navigation in Unconstrained Environments at ECCV 2018.
  • I gave an invited talk at the workshop 3D Reconstruction in the Wild at ECCV 2018.
  • I served as workshop co-chair for CVPR 2018.
  • 2018 Papers: 1 Paper accepted in ICML 2018, 2 papers in CVPR 2018, 1 paper in 3DV 2018, 2 papers in ECCV 2018
  • Visited Elder's laboratory in lovely York University and gave an invited talk on 04/06/2018.
  • 2018 Area Chair duties: CVPR 2018, ICVGIP 2018, computer vision co-chair in ISVC 2018
  • Joined the faculty at the University of Utah in January 2017.
  • Left Mitsubishi Electric Research Laboratories (MERL) after spending 8 wonderful years.


Sample Research Videos


New SLC Marathon dataset (> 26 miles) will be released as part of semantic boundary based localization!

Holistic Scene Understanding for Autonomous Driving

Semantic Region and Boundary Segmentation methods

Line Reconstruction from a Single Image

High-Performance and Tunable Stereo Reconstruction

SKYLINE2GPS: Localization in Urban Canyons using OmniSkylines

Image-based Localization using points and lines in Urban Canyons

RGBD-SLAM using points and planes

Srikumar Ramalingam, Associate Professor, School of Computing, The University of Utah, Room 3464, 50 Central Campus Drive, Salt Lake City, UT 84112, Mail: srikumar AT cs DOT utah DOT edu