I’m a PhD candidate in Computer Science and Engineering at the Hong Kong University of Science and Technology, supervised by Prof. Tristan Braud. I am fortunate to visit the Active Vision Laboratory, University of Oxford advised by Prof. Victor Prisacariu. I received my bachelor’s degree from Shanghai Jiao Tong University. Research Focus: Visual Localization, 3D Reconstruction, improve the user’s Augmented Reality (AR) and Virtual Reality (VR) experience.
🔥 News
- 2024.04: 🎉🎉 Start visiting in the Active Vision Laboratory, University of Oxford! Thanks Shuai Chen for showing me around the University and Lab!
- 2024.02: 🎉🎉 One paper is accepted in Conference on Computer Vision and Pattern Recognition (CVPR) 2024. Thanks to all coauthors!
- 2024.01: 🎉🎉 One paper is accepted in International Conference on Robotics and Automation (ICRA) 2024. Thanks to all coauthors!
📝 Publications and Preprints
* equal contribution
GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting
Changkun Liu, Shuai Chen, Yash Bhalgat, Siyan Hu, Ming Cheng, Zirui Wang, Victor Adrian Prisacariu, Tristan Braud. (arXiv 2024)
- GSLoc is a camera pose refinement framework that leverages 3D Gaussian Splatting for scene representation, combined with the 3D foundation model, MASt3R.
360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries
Huajian Huang*, Changkun Liu*, Yipeng Zhu, Hui Cheng, Tristan Braud, and Sai-Kit Yeung (CVPR 2024)
- 360Loc is the first dataset and benchmark that explores the challenge of cross-device visual positioning, involving 360° reference frames, and query frames from pinhole, ultra-wide FoV fisheye, and 360° cameras.
Changkun Liu, Shuai Chen, Yukun Zhao, Huajian Huang, Victor Prisacariu, and Tristan Braud (ICRA 2024)
- This work introduces a novel APR-agnostic framework, HR-APR, that formulates uncertainty estimation as cosine similarity estimation between the query and database features.
-
LiteVLoc: Map-Lite Visual Localization for Image Goal Navigation, Jianhao Jiao, Jinhao He, Changkun Liu, Sebastian Aegidius, Xiangcheng Hu, Tristan Braud, Dimitrios Kanoulas. arXiv 2024
-
AIR-HLoc: Adaptive Retrieved Images Selection for Efficient Visual Localisation, Changkun Liu, Jianhao Jiao, Huajian Huang, Zhengyang Ma, Dimitrios Kanoulas, Tristan Braud. arXiv 2024
-
MARViN: Mobile AR Dataset with Visual-Inertial Data, Changkun Liu*, Yukun Zhao*, Tristan Braud. IEEE VR 2024 Workshop
-
MobileARLoc: On-device Robust Absolute Localisation for Pervasive Markerless Mobile AR, Changkun Liu*, Yukun Zhao*, Tristan Braud. PerCom 2024 Workshop
-
VR PreM+: An Immersive Pre-learning Branching Visualization System for Museum Tours, Ze Gao, Xiang Li, Changkun Liu, Xian Wang, Anqi Wang, Liang Yang, Yuyang Wang, Pan Hui, Tristan Braud. Chinese CHI 2023
📖 Educations
- 2021.09 - now, Ph.D. in Computer Science and Engineering, The Hong Kong University of Science and Technology.
- 2017.09 - 2021.06, Bachelor of Engineering in Electronic Science and Technology, Shanghai Jiao Tong University.
💻 Experience
- 2024.04 - now, Visiting Research Student at the University of Oxford, Oxford, UK.
- 2020.06 - 2021.05, Intel Asia-Pacific R&D Ltd., Shanghai, China.
- 2019.07 - 2019.08, University of Washington, Seattle, US.
🎖 Honors and Awards
- 2024 Overseas Research Award in HKUST
- 2021-now Postgraduate Studentship in HKUST
- 2021 Outstanding Graduate of Shanghai Jiao Tong University (Top 20%)
- 2020 Second-Class Scholarship Awarded by SCSK, Kabuskiki Kaisha in SJTU (Top 4%)
- 2020 Class B Scholarship of SJTU
- 2018, 2019 Class C Scholarship of SJTU
Academic Service
- Reviewer: ICRA