I'm a second-year Ph.D. student 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. I am a member of AnySyn3D, a research interest group focusing on various topics related to 3D. My research mainly concentrates on 3D vision and graphics. I currently work on reconstruction, generation, and editing of digital avatars. Early interests include visual SLAM and MVS.
2024.02: ππ One paper accepted to CVPR 2024.
2023.09: ππ I start pursuing my Ph.D. degree at HKUST.
π Publications
GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor Xiangyue Liu, Kunming Luo, Heng Li, Qi Zhang, Yuan Liu, Li Yi, Ping Tan
3DV 2025
We introduce GaussianAvatar-Editor, an innovative framework for text-driven editing of animatable Gaussian head avatars that can be fully controlled in expression, pose, and viewpoint.
GenN2N: Generative NeRF2NeRF Translation Xiangyue Liu, Han Xue, Kunming Luo, Ping Tan, Li Yi
CVPR 2024[Paper][Project Page][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.
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 linesβ 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.
π Cooking
I love sharing food with loved ones. Check out what I cooked here.
I love exploring coffee shops. Check out those healing moments here.
π Awards
2021.06: Excellent Graduate in Beijing
2020.08: 2nd in IJCAI 3D AI Challenge: Instance Segmentation (2/559) website
2016.10: National College Students Innovation and Entrepreneurship Training Program
π 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