Visesh Chari

I spent four beautiful years doing my PhD right below the French Alpes, at INRIA Rhône Alpes. Before that, I got my Bachelors in Computer Science (with honours) and MS in Computer Vision from IIIT-Hyderabad

Over the last few years, I have had the opportunity to work with amazing people like Peter Sturm, Ivan Laptev, Josef Sivic, CV Jawahar, PJ Narayanan and several others.

While not working, or discussing AI with friends, I spend my time hiking, biking, running along west cliff drive and occasionally dabbling in sports like cricket, ping pong and tennis.

Complete publication list can be found via my google scholar. Selected publications below

• New Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving, Jingxiao Zheng, Xinwei Shi, Alexander Gorban, Junhua Mao, Yang Song, Charles R. Qi, Ting Liu, Visesh Chari, Andre Cornman, Yin Zhou, Congcong Li and Dragomir Anguelov. ArXiV 2021
• Multi-Hypothesis Pose Networks: Rethinking Top-Down Pose Estimation, Rawal Khirodkar, Visesh Chari, Amit Agrawal and Ambrish Tyagi. ICCV 2021
• Learning to generate synthetic data via compositing, Shashank Tripathi, Siddhartha Chandra, Amit Agrawal, Ambrish Tyagi, James Rehg, and Visesh Chari. CVPR 2019
• View-graph Selection Framework for SfM, Rajvi Shah, Visesh Chari, P J Narayanan. ECCV 2018
• Monocular Reconstruction of Vehicles: Combining SLAM with Shape Priors, Falak Chhaya, Dinesh Reddy, Sarthak Upadhyay, Zeeshan Zia, Madhava Krishna, ICRA 2016
• On pairwise cost for multi-object network flow tracking, Visesh Chari, Simon-Lacoste Julien, Ivan Laptev, Josef Sivic. CVPR 2015
• A theory of refractive photo-light path triangulation, Visesh Chari, Peter Sturm. CVPR 2013
• A theory of multi-layer flat refractive geometry, Amit Agrawal, Srikumar Ramalingam, Yuichi Taguchi, Visesh Chari. CVPR 2012 (oral)
• Convex bricks: A new primitive for visual hull modeling and reconstruction, Visesh Chari, Amit Agrawal, Yuichi Taguchi, Srikumar Ramalingam. ICRA 2012

1. New [Feb 2022] Our work on "Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving" is up on ArXiV.
2. [Nov 2021] Three new patents issued in personalized 3D body models and synthetic data generation!
3. [July 2021] I joined Waymo as a Senior Software Engineer, working with Yang Song. Looking forward to working in the AV space!
4. [May 2021] Our work with my intern Rawal Khirodkar, "Multi-Hypothesis Pose Networks: Rethinking Top-Down Pose Estimation" has been accepted to ICCV 2021! Check it out!
5. [Jan 2021] Our work on "Multi-Hypothesis Pose Networks: Rethinking Top-Down Pose Estimation" is up on ArXiV. We show state-of-the-art results for human pose estimation on crowded datasets like OCHuman.
6. [August 2020] Shashank joins MPI Tüebingen for his PhD. Shashank was my intern in 2018. Our work resulted in a paper at CVPR 2019.
7. [September 2019] Our work on "Towards Accurate 3D Human Body Reconstruction from Silhouettes" accepted at 3DV 2019
8. [August 2019] Rajvi joins Facebook Reality Labs. I advised her during her PhD at IIIT-Hyderabad in 2015. Our work was published in ECCV 2018.
9. [June 2019] Our work on "Learning to generate synthetic data via compositing" accepted at CVPR 2019
10. [Jan 2019] Mallikarjun joins MPI Saarbrücken for his PhD. I advised Mallikarjun for his MS projects at IIIT-Hyderabad in 2015. Our work was published in WACV 2016.
11. [September 2018] Our work on "View-graph Selection Framework for SfM" accepted at ECCV 2018
12. [December 2017] Our work on "A Unified View-Graph Selection Framework for Structure from Motion" published as ArXiV Report
13. [August 2017] Siddharth joins University of Heidelberg for his PhD. I advised Siddharth for his MS project at IIIT-Hyderabad in 2015. Our work was published in ICRA 2016.
14. [January 2017] Dinesh joins CMU for PhD. I advised Dinesh for his Masters projects at IIIT-Hyderabad in 2015. We published two papers in ICRA 2016 and IROS 2015.
15. [May 2016] Our work on "Rolling shutter and motion blur removal for depth cameras" accepted at ICRA 2016
16. [May 2016] Our work on "Monocular Reconstruction of Vehicles: Combining SLAM with Shape Priors" accepted at ICRA 2016
17. [March 2016] Our work on "Face fiducial detection by consensus of exemplars" accepted at WACV 2016