Khang Truong Giang
Researcher
Seoul, South Korea
Hello, my name is Khang Truong Giang (please call me Khang for short). I am currently an engineer at 42dot, South Korea. I obtained my PhD and MS degree from KAIST in 2024 and 2021, respectively. During this time, I am fortunate to be advised by Prof. Sungho Jo and co-advised by Prof. Soohwan Song. Before joining KAIST, I did my Bachelor at Hanoi University of Science and Technology (HUST), Vietnam.
Research interests: I am currently working on building robust perception models for autonomous driving. Also, I am interested in research problems in 3D reconstruction and neural rendering. I have developed various advanced deep-learning models tailored to resolve several tasks in 3D reconstruction, including feature matching, visual localization, and multi-view depth estimation. Furthermore, I actively contribute research codes on Github, which are widely utilized by hundreds of users globally.
news
| Aug 13, 2025 | Our works on Gaussian Splatting SLAM has been accepted to IJCAI (CORE A*) annd IEEE Access this year. |
|---|---|
| Oct 17, 2024 | Feature matching TopicFM+ is accepted at IEEE Transactions on Image Processing |
| Aug 13, 2024 | I was invited to serve as Program Committee at AAAI2025 |
| Jul 15, 2024 | I am starting as a 3D Vision Engineer at 42dot |
| May 24, 2024 | I was selected as an outstanding reviewer at CVPR2024. |
| Feb 26, 2024 | Our visual localization paper is accepted at CVPR 2024. |
| Nov 20, 2022 | Two paper accepted at AAAI-23 and Pattern Recognition!  |
selected publications
(*) denotes equal contribution, (+) denotes corresponding authors-
Online 3D Gaussian Splatting Modeling with Novel View SelectionIn Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25 2025 -
Topicfm+: Boosting accuracy and efficiency of topic-assisted feature matchingIEEE Transactions on Image Processing 2024
