Xiangyue Liu (刘襄阅)

PhD Candidate

Hong Kong University of Science and Technology
Clear Water Bay, Kowloon, HongKong

Email: xliufz [at] connect [dot] ust [dot] hk


Biography

I'm a second-year PhD candidate of ECE at The Hong Kong University of Science and Technology (HKUST), under the supervision of Prof. Ping Tan. I was a visiting student (RA) at Tsinghua University advised by Prof. Li Yi and Prof. Yang Gao. I obtained my M.S. in Software Engineering from Beihang University, and B.Eng in Software Engineering from Northeast Normal University. I am a member of AnySyn3D.

My research interests lie in Computer Vision and Robotics. From 2023, I started to do some research on generative text-driven editing for 3D/4D scenes (GenN2N, GaussianAvatar-Editor). Now, I focus on designing novel generative models, vision language models (VLMs), and vision-language-action models (VLA).

Feel free to contact me if you are interested in discussing or collaborating with me.

News

Internship

               

Tencent AI Lab

Topic: Digital Avatar, Talking Head Video Generation

Sept. 2023 - Dec. 2024, Tencent AI Lab, Shenzhen, worked with Dr. Qi Zhang and Dr. Yuxin Wen

Megvii Research

Topic: NeRF, Monocular Video Reconstruction

Apr. 2022 - Aug. 2023, AIC Group, Beijing, worked with Weixin Xu, Yi Yang, and Dr. Shuchang Zhou

Topic: Deep MVS

Jun. 2021 - Apr. 2022, 3D Vision Group, Beijing, worked with Haotian Zhang and Xiao Liu

Topic: Ray-point-ray Reconstruction in Visual SLAM

Aug. 2019 - Apr. 2020, SLAM&AR Group, Beijing, worked with Dr. Yijia He and Xiao Liu

Education & Visiting

The Hong Kong University of Science and Technology, Hong Kong

PhD Candidate in Von Neumann Institute, HKUST

Advisor: Prof. Ping Tan

Sep. 2023 - Future

Tsinghua University, China

Research Assistant in IIIS, Tsinghua University

Advisors: Prof. Li Yi and Prof. Yang Gao

Aug. 2021 - Aug. 2023

Beihang University, China

Master of Software Engineering

Sep. 2018 - Jun. 2021

Northeast Normal Univesity, China

Bachelor of Software Engineering

Sep. 2014 - Jun. 2018

Selected Publications

                                   
/*Conference*/

GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor

Xiangyue Liu, Kunming Luo, Heng Li, Qi Zhang, Yuan Liu, Li Yi, Ping Tan

3DV 2025

[paper] [project page] [code]

GenN2N: Generative NeRF2NeRF Translation

Xiangyue Liu, Han Xue, Kunming Luo, Ping Tan, Li Yi

CVPR 2024

[paper] [project page] [code]

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]

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]

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] [project page] [code]

Structure Reconstruction Using Ray-Point-Ray Features: Representation and Camera Pose Estimation

Yijia He*, Xiangyue Liu*, Xiao Liu, Ji Zhao

ICRA 2021

[paper]

2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020

Kai Jiang*, Xiangyue Liu*, Zhang Ju*, Xiang Luo

IJCAI Workshop 2020

[paper]

Honors &Awards

[06/2021] Outstanding Graduate Student of Beijing.
[08/2020] Second Place in 3D Instance Segmentation Challenge at IJCAI 2020.
[10/2016] National College Students Innovation and Entrepreneurship Training Program.

Community Services

Teaching Assistant

2024-2025FallComputer Communication Networks (HKUST, ELEC3120)
2023-2024SpringElectronic and Information Technology (HKUST, ELEC1010)


© Xiangyue Liu