|
Debao Huang I'm a PhD candidate in the Geospatial Data Analytics Group at The Ohio State University. I started in January 2021 and am supervised by Prof. Rongjun Qin. My research interests lie in 3D reconstruction and uncertainty quantification. I am working on multiple projects funded by ONR, IARPA, AFRL and NSF to solve 3D geometry problems and tasks. Keywords: Photogrammetry, Computer Vision, Remote Sensing, Machine Learning, Artificial Intelligence, Structure-from-Motion (SfM), 3D Gaussian Splatting (3DGS), Uncertainty Modeling. |
|
News |
|
03/2025 |
Our new papers of dynamic 3D Gaussian Splatting and uncertainty quantification, got accepted to ISPRS Geospatial Week 2025. |
|
11/2024 |
I was honored to be an outstanding reviewer for the 35th British Machine Vision Conference (BMVC 2024). |
|
04/2024 |
Our new paper of incorporating motion constraints in Bundle Adjustment of Structure-from-Motion for uncalibrated multi-camera systems, got published in ISPRS Journal of Photogrammetry and Remote Sensing. |
|
04/2024 |
Our new paper of proposing a new scheme to scale up NeRF for large-scale aerial images, got published in The Photogrammetric Record. |
|
06/2023 |
Our new paper of the preliminary study of uncertainty quantification in MVS, got accepted to ISPRS Geospatial Week 2023. |
|
05/2022 |
Our new paper of baseline constraint in BA for SfM using uncalibrated multi-camera systems, got accepted to ISPRS Congress 2022. |
|
04/2022 |
Our new paper of evaluation of PlanetScope images for 3D reconstruction and change detection, got published in GIScience & Remote Sensing Journal. |
|
08/2021 |
Our new paper of 3D change detection of a building deconstruction event using UAV images, got published in International Journal of Digital Earth. |
My Research |
|
BUNDLE ADJUSTMENT WITH MOTION CONSTRAINTS FOR UNCALIBRATED MULTI-CAMERA SYSTEMS AT THE GROUND LEVEL
Debao Huang, Rongjun Qin, Mostafa Elhashash ISPRS Journal of Photogrammetry and Remote Sensing, 2024 paper | video This paper derives novel geometric constraints in BA of SfM pipeline that assumes minimal knowns about the uncalibrated multi-camera systems at the ground level. Our proposed constraints are effective in correcting topographical errors (i.e., trajectory drifts) of the reconstruction. It benefits the broader use of photogrammetry with low-cost and non-expert use cases to generate 3D products with improved accuracy. |
|
MULTI-TILING NEURAL RADIANCE FIELD (NERF)—GEOMETRIC ASSESSMENT ON LARGE-SCALE AERIAL DATASETS
Ningli Xu, Rongjun Qin, Debao Huang, Fabio Remondino The Photogrammetric Record, 2024 paper | video | code This paper provides multi-camera tiling (MCT) strategy to scale the NeRF on large-scale aerial datasets and a thorough geometry assessment of NeRF. |
|
A CRITICAL ANALYSIS OF INTERNAL RELIABILITY FOR
UNCERTAINTY QUANTIFICATION OF DENSE IMAGE MATCHING IN MULTI-VIEW
STEREO
Debao Huang, Rongjun Qin ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2023 paper This paper presents preliminary study of metrics in the dense matching and MVS fusion process, to learn heuristic correlation for propagating errors to the final point clouds. |
|
CONSTRAINED BUNDLE ADJUSTMENT FOR STRUCTURE
FROM MOTION USING UNCALIBRATED MULTI-CAMERA SYSTEMS
Debao Huang, Mostafa Elhashash, Rongjun Qin ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022 paper This paper proposes a bundle adjustment (BA) solution for uncalibrated cameras with overlapping views by incorporating a so-called baseline constraint which builds the link between two cameras that are static to each other. |
|
AN EVALUATION OF PLANETSCOPE IMAGES FOR 3D
RECONSTRUCTION AND CHANGE DETECTION – EXPERIMENTAL VALIDATIONS WITH
CASE STUDIES
Debao Huang, Yang Tang, Rongjun Qin GIScience & Remote Sensing, 2022 paper | video This paper comprehensively evaluates the 3D potential of PlanetScope images by performing accuracy analysis for both 3D reconstruction and change detection. |
|
A VOLUMETRIC CHANGE DETECTION FRAMEWORK USING
UAV OBLIQUE PHOTOGRAMMETRY – A CASE STUDY OF ULTRA-HIGH-RESOLUTION
MONITORING OF PROGRESSIVE BUILDING COLLAPSE
Ningli Xu, Debao Huang, Shuang Song, Xiao Ling, Chris Strasbaugh, Alper Yilmaz, Halil Sezen, Rongjun Qin International Journal of Digital Earth, 2021 paper | video This paper presents an unmanned aerial vehicle (UAV) based fine-scale 3D change detection and monitoring of progressive collapse performance of a building during a demolition event. |
Software and Demo |
| 1. Photogrammetry toolkit: full 3D reconstruction pipeline from SfM, MVS, meshing to texturing. |
| 2. Quantification framework: estimating and encoding error covariance of 3D points, visualization in desktop GUI and VR. |
| 3. Dynamic urban scene modeling: dynamic 3D Gaussian Splatting from UAV full motion videos. |
Academic Services |
| I serve as a peer reviewer for: |
|
|
Professional Services |
| I am a Federal Aviation Administration (FAA) certificated remote pilot, which allows me to collect UAV data for both research and commercial purposes in the US. I have conducted many data collection and surveying tasks that are utilized in our projects and research. The following map shows the flight missions I have conducted on campus. |
|