Khiem Vuong

I'm a PhD student at Carnegie Mellon University (Robotics Institute), where I'm extremely fortunate to be 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 on VI-SLAM and egocentric scene understanding.

I'm currently interning at Meta Reality Labs, exploring the intersection of video generative models and 3D/4D reconstruction for building a generative world model.

I'm always happy to chat or collaborate — feel free to reach out at kvuong@andrew.cmu.edu!

Email Resume GitHub Scholar
Khiem Vuong
News
05/2026 Interning at Meta Reality Labs this summer (working with Peter Hedman and Peter Kontschieder)!
03/2025 AerialMegaDepth is accepted to CVPR 2025!
02/2025 I will join Apple as an intern this summer (VIO/SLAM team, Video Computer Vision)!
03/2024 WALT3D is accepted to CVPR 2024 as an Oral (top 0.8%)!
Publications
FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors
Khiem Vuong, Deva Ramanan*, Srinivasa Narasimhan*
arXiv 2026   (* equal advising)  ·  more details coming soon :)
A single generalist video model that fixes rendering artifacts from any 3D representation — 3DGS, NeRF, mesh, or sparse point clouds — producing photorealistic, 3D-consistent videos.
Novel View Synthesis as Video Completion
Qi Wu, Khiem Vuong, Minsik Jeon, Srinivasa Narasimhan, Deva Ramanan
arXiv 2026
paper project
Adapting pretrained video diffusion models for permutation-invariant sparse-view novel view synthesis, achieving SOTA results with minimal training data.
MapSplat
MapSplat: Feed-Forward Geometry Beyond Visible Surfaces
Mehar Khurana, Nikhil Keetha, Khiem Vuong, Marcel Schreiber, Tarasha Khurana, Deva Ramanan
arXiv 2026  ·  more details coming soon :)
Extending 2.5D feed-forward geometry predictors to "2.6D" by replacing per-pixel depth supervision with differentiable 3D Gaussian splatting, enabling supervision from novel views.
ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones
Anurag Ghosh, Shen Zheng, Robert Tamburo, Khiem Vuong, Juan Alvarez-Padilla, Hailiang Zhu, Michael Cardei, Nicholas Dunn, Christoph Mertz, Srinivasa G. Narasimhan
ICCV 2025
paper project code
Largest open-source dataset for studying autonomous driving in work zones.
AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
Khiem Vuong, Anurag Ghosh, Deva Ramanan*, Srinivasa Narasimhan*, Shubham Tulsiani*
CVPR 2025   (* equal contribution/advising)
paper project 3D viewer code
A scalable data generation framework that combines mesh-renderings with real images, enabling robust 3D reconstruction across extreme viewpoint variations.
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
CVPR 2024 (Oral, top 0.8%)   (* equal contribution)
paper project video
Automatically generate realistic training data from time-lapse videos for reconstructing dynamic objects under occlusion.
Toward Planet-Wide Traffic Camera Calibration
Khiem Vuong, Robert Tamburo, Srinivasa G. Narasimhan
WACV 2024
paper project video code
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
CVPR 2022 (Oral, top 4.2%)
paper project video code
Extension of the spatial rectifier to the multi-directional case, applying to depth/surface normal prediction from egocentric view.
Surface Normal Estimation of Tilted Images via Spatial Rectifier
Tien Do, Khiem Vuong, Stergios I. Roumeliotis, Hyun Soo Park
ECCV 2020 (Spotlight, top 3%)
paper project video code
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
ICRA 2021
paper 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
IROS 2020
paper code
Depth estimation by completing a sparse VI-SLAM point cloud using planar constraint from robust surface normal prediction.
Academic Services & Awards

Awards: Outstanding Reviewer, CVPR 2026

Teaching Assistant: Computer Vision (16-720, Fall 2024) and Computer Vision (16-385, Spring 2025) at CMU

Conference Reviewer: NeurIPS, CVPR, ICCV, ECCV, WACV, IROS, AAAI, ICLR

Journal Reviewer: IJCV, TPAMI

Experience
Meta Reality Labs
Research Scientist Intern — Reality AI Research
Summer 2026
Building a generative world model. (Hosts: Peter Hedman, Peter Kontschieder)
Apple Inc.
CV/ML Intern — Video Computer Vision (VIO/SLAM)
Summer 2025
Building 3D foundation models for AR/VR applications. (Host: Stergios Roumeliotis)
Carnegie Mellon University, Robotics Institute
M.S. in Robotics (2021 – 2023)
Ph.D. in Robotics (2023 – Present)
Working on 3D reconstruction and generative world models with Deva Ramanan and Srinivasa Narasimhan
University of Minnesota
Research Assistant (2019 – 2021)
Working on learning-based VI-SLAM and egocentric 3D vision with Stergios Roumeliotis and Hyun Soo Park
Enfusion Systems (now CWAN)
Software Engineering Intern
Summer 2019
Working on Portfolio Management Systems (PMS)