|
I'm a 2nd-year PhD student in the Robotics Institute, Carnegie Mellon University, co-advised by Deva Ramanan and Srinivasa Narasimhan. Previously, I received my BS in Computer Science from University of Minnesota, working with Stergios Roumeliotis and Hyun Soo Park. I'm interested in computer vision, robotics, and machine learning, especially 3D/4D reconstruction and visual scene understanding. Feel free to reach out to me at kvuong at andrew.cmu.edu! Email | Resume | GitHub | Google Scholar |
|
|
|
|
 |
Khiem Vuong, Anurag Ghosh, Deva Ramanan*, Srinivasa Narasimhan*, Shubham Tulsiani* Conference on Computer Vision and Pattern Recognition (CVPR), 2025 (* equal contribution/advising) paper | project page | 3D web viewer | code A scalable data generation framework that combines mesh-renderings with real images, enabling robust 3D reconstruction across extreme viewpoint variations (e.g., aerial-ground). |
 |
Khiem Vuong*, N Dinesh Reddy*, Robert Tamburo, Srinivasa G. Narasimhan Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Oral, top 0.8%) (* equal contribution) paper | project page | video | code Automatically generate realistic training data from time-lapse videos for reconstructing dynamics objects (people, vehicle) under occlusion. |
 |
Khiem Vuong, Robert Tamburo, Srinivasa G. Narasimhan Winter Conference on Applications of Computer Vision (WACV), 2024 paper | project page | video | code 3D scene reconstruction and precise localization of over 100 real-world traffic cameras. |
 |
Tien Do, Khiem Vuong, Hyun Soo Park Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral, top 4.2%) paper | project page | video | code 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. |
 |
Tien Do, Khiem Vuong, Stergios I. Roumeliotis, Hyun Soo Park European Conference on Computer Vision (ECCV), 2020 (Spotlight, top 3%) paper | project page | video | code Robust surface normal estimation by spatially rectifying image to the densely distributed orientations. |
 |
Tong Ke, Tien Do, Khiem Vuong, Kourosh Sartipi, Stergios I. Roumeliotis International Conference on Robotics and Automation (ICRA), 2021 paper | code Depth estimation by multiview triangulation, followed by an iterative depth refinement module that preserves estimates with high triangulation confidence. |
 |
Kourosh Sartipi, Tien Do, Tong Ke, Khiem Vuong, Stergios I. Roumeliotis International Conference on Intelligent Robots and Systems (IROS), 2020 paper | code Depth estimation by completing a sparse VI-SLAM point cloud using planar constraint from robust surface normal prediction. |
|
|
|