Khiem Vuong

I'm joining The Robotics Institute, part of the School of Computer Science (SCS) at Carnegie Mellon University, as a Master's student in Robotics.

I received my Bachelor's degree in Computer Science from University of Minnesota where I worked in the Multiple Autonomous Robotic Systems (MARS) Lab under the guidance of Prof. Stergios Roumeliotis. I was also advised by Prof. Hyun Soo Park and Prof. Lana Yarosh on various computer vision and HCI research projects. I spent an amazing summer at Enfusion Systems as a software engineering intern during my sophomore year.

I'm interested in computer vision, machine learning, and robotics. Most of my research is about 3D perception and visual scene understanding.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo
  News
  • [Mar. 2021] Our paper Deep Multi-view Depth Estimation with Predicted Uncertainty is accepted to ICRA 2021.
  • [Jul. 2020] Our paper Surface Normal Estimation of Tilted Images via Spatial Rectifier is accepted to ECCV 2020 as a spotlight presentation.
  • [Jun. 2020] Our paper Deep Depth Estimation from Visual-Inertial SLAM is accepted to IROS 2020.
  Research/Publications
project image Deep Multi-view Depth Estimation with Predicted Uncertainty
Tong Ke, Tien Do, Khiem Vuong, Kourosh Sartipi, and Stergios I. Roumeliotis
IEEE International Conference on Robotics and Automation (ICRA), 2021
[pdf] [code]

Estimating dense depth and its uncertainty from a sequence of images by leveraging a dense optical flow network to triangulate initial depth maps and refine them through an iterative refinement module.

project image Surface Normal Estimation of Tilted Images via Spatial Rectifier
Tien Do, Khiem Vuong, Stergios I. Roumeliotis, and Hyun Soo Park
European Conference on Computer Vision (ECCV), 2020

(Spotlight Presentation)


[pdf] [website] [video] [code]

Surface normal estimation of tilted images by leveraging a spatial rectifier that is learned to transform the surface normal distribution of a tilted image to the rectified one that matches the gravity-aligned training data distribution.

project image Deep Depth Estimation from Visual-Inertial SLAM
Kourosh Sartipi, Tien Do, Tong Ke, Khiem Vuong, and Stergios I. Roumeliotis
IEEE/RSJ International Conference on Intelligent Robots and System (IROS), 2020
[pdf] [code]

Dense depth estimation from sparse depth points (computed from a Visual-Inertial SLAM system) and RGB images of indoor scenes.

  Work Experience
project image Research Assistant Sep. 2019 - Present
Multiple Autonomous Robotic Systems (MARS) Laboratory
Advisor: Prof. Stergios I. Roumeliotis
project image Software Engineering Intern Jun. 2019 - Aug. 2019
Enfusion Systems
Team: Backend services, Portfolio Management Systems (PMS)
project image Research Assistant Jun. 2018 - May 2019
GroupLens Research
Advisor: Prof. Lana Yarosh

Template from Jon Barron. Last modified: June 8th, 2021.