Xiangyue Liu

I'm a Ph.D. student (2023.9-) at HKUST, advised by Prof. Ping Tan. Before that, I was a visiting student (RA) at Tsinghua University, advised by Prof. Li Yi and Prof. Yang Gao. Previously, I completed my Master's from Beihang University.

My research focuses on deep learning and computer vision, with a strong emphasis on 3D/4D Generation/ Reconstruction/ Editing utilizing deep generative models. Early interests were visual SLAM and MVS.

Google Scholar · Github · Twitter · Email

🔥 News

NEW [2024/02] One paper accepted to CVPR 2024 🎉.
NEW [2023/09] I start pursuing my Ph.D. degree at HKUST.
[2022/06] Two papers accepted to ECCV 2022.
[2022/03] One paper accepted to CVPR 2022.

📑 Publications

	GenN2N: Generative NeRF2NeRF Translation Xiangyue Liu, Han Xue, Kunming Luo, Ping Tan, Li Yi CVPR 2024 [Project Page] [Paper] [Code] We present GenN2N, a unified NeRF-to-NeRF translation framework for various NeRF translation tasks such as text-driven NeRF editing, colorization, super-resolution, inpainting, etc. GenN2N achieves all these NeRF editing tasks by employing a plug-and-play image-to-image translator to perform editing in the 2D domain and lifting 2D edits into the 3D NeRF space.
	Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives Wentao Yuan, Qingtian Zhu, Xiangyue Liu, Yikang Ding, Haotian Zhang, Chi Zhang ECCV 2022 [Paper] [Code] We propose a training paradigm for Implicit Neural Representations (INRs) that encode image derivatives in addition to image values in the neural network.
	KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo Yikang Ding, Qingtian Zhu, Xiangyue Liu, Wentao Yuan, Haotian Zhang, Chi Zhang ECCV 2022 [Paper] [Code] We propose a novel self-supervised training pipeline for MVS based on knowledge distillation, termed KD-MVS, which mainly consists of self-supervised teacher training and distillation-based student training.
	TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers Yikang Ding, Wentao Yuan, Qingtian Zhu, Haotian Zhang, Xiangyue Liu, Yuanjiang Wang, Xiao Liu CVPR 2022 [Paper] [Code] We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer to leverage self- and cross- attention to aggregate long-range context information within and across images.
	Structure Reconstruction Using Ray-Point-Ray Features: Representation and Camera Pose Estimation Yijia He, Xiangyue Liu, Xiao Liu, Ji Zhao ICRA 2021 [Paper] Straight line features have been increasingly utilized in visual SLAM and 3D reconstruction systems. The straight lines’ parameterization, parallel constraint, and coplanar constraint are studied in many recent works. In this paper, we explore the novel intersection constraint of straight lines for structure reconstruction.

🌏 Challenge

2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020 (2/559)
Kai Jiang*, Xiangyue Liu*, Zhang Ju*, Xiang Luo
IJCAI 2020 workshop [Paper]

🏆 Awards

[2021/06] Excellent Graduate in Beijing
[2020/08] 2^nd in IJCAI 3D AI Challenge: Instance Segmentation (2/559) website
[2016/10] National College Students Innovation and Entrepreneurship Training Program

🎓 Educations

2023.09 - future: Ph.D. in Electronic and Computer Engineering, Hong Kong University of Science and Technology
2018.09 - 2021.06: M.Sc. in Software Engineering, Beihang University
2014.09 - 2018.06: B.Eng. in Software Engineering, Northeast Normal University

👩🏻‍💻 Internships

2021.08 - 2023.08: Tsinghua University, IIIS, supervised by Prof. Li Yi, and Prof. Yang Gao
2022.04 - 2023.08: MEGVII Research, AIC, supervised by Weixin Xu, Yi Yang, and Dr. Shuchang Zhou
2021.06 - 2022.04: MEGVII Research, 3D Vision, supervised by Haotian Zhang, and Xiao Liu
2019.08 - 2020.04: MEGVII Research, SLAM&AR, supervised by Dr. Yijia He, and Xiao Liu

Last update: Apr. 2024