I'm a PhD student in the Robotics Institute at Carnegie Mellon University, advised by Srinivasa Narasimhan.

Previously, I received my BS in Computer Science from University of Minnesota, working with Stergios Roumeliotis and Hyun Soo Park. I also spent a summer at Enfusion Systems as a SWE intern during my undergrad.

I'm interested in computer vision, robotics, and machine learning, especially 3D/4D reconstruction and visual scene understanding.

Email: kvuong [at]


WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion

Khiem Vuong, N Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan

In CVPR 2024 (Oral, Top 0.8%)


Website arXiv Code Video

Automatically generate realistic training data from time-lapse videos for reconstructing dynamics objects (people, vehicle) under occlusion.

Toward Planet-Wide Traffic Camera Calibration

Khiem Vuong, Robert Tamburo, Srinivasa G. Narasimhan

In WACV 2024


Website arXiv Code Video

3D scene reconstruction and precise localization of over 100 real-world traffic cameras.

Egocentric Scene Understanding via Multimodal Spatial Rectifier

Tien Do, Khiem Vuong, Hyun Soo Park

In CVPR 2022 (Oral, Top 4.2%)


Website arXiv Code Video

Extension of the spatial rectifier to the multi-directional case, applying to depth/surface normal prediction from egocentric view, accompanied by a novel egocentric RGB-D dataset.

Surface Normal Estimation of Tilted Images via Spatial Rectifier

Tien Do, Khiem Vuong, Stergios I. Roumeliotis, Hyun Soo Park

In ECCV 2020 (Oral, Top 2%)


Website arXiv Code Video

Robust surface normal estimation by spatially rectifying image to the densely distributed orientations.

Deep Multi-view Depth Estimation with Predicted Uncertainty

Tong Ke, Tien Do, Khiem Vuong, Kourosh Sartipi, Stergios I. Roumeliotis

In ICRA 2021


arXiv Code

Depth estimation by multiview triangulation, followed by an iterative depth refinement module that preserves estimates with high triangulation confidence.

Deep Depth Estimation from Visual-Inertial SLAM

Kourosh Sartipi, Tien Do, Tong Ke, Khiem Vuong, Stergios I. Roumeliotis

In IROS 2020


arXiv Code

Depth estimation by completing a sparse VI-SLAM point cloud using planar constraint from robust surface normal prediction.



Carnegie Mellon University
Aug 2023 - present
Ph.D. in Robotics
Advisor: Srinivasa Narasimhan

Carnegie Mellon University
Aug 2021 - Aug 2023
M.S. in Robotics
GPA: 4.17/4.3
Advisor: Srinivasa Narasimhan

University of Minnesota
Aug 2017 - Aug 2021
B.S. in Computer Science (with high distinction)
GPA: 4.0/4.0
Advisor: Stergios Roumeliotis & Hyun Soo Park


Enfusion Systems
Jun 2019 - Aug 2019
Software Engineering Intern
Team: Portfolio Management Systems (PMS)