Weijie Lyu
I am a third year EECS Ph.D. student at University of California, Merced, advised by Prof. Ming-Hsuan Yang .
I obtained my Master of Science in Computer Science degree from University of Illinois at Urbana-Champaign, advised by Prof. Derek Hoiem . I was also fortunate to work with Prof. Bo Li .
I obtained my Bachelor of Engineering degree from ShanghaiTech University, majoring in Computer Science and Technology. I spent my junior year as a visiting student and undergraduate researcher at University of California, Berkeley.
Email  / 
CV  / 
Google Scholar  / 
Semantic Scholar  / 
GitHub  / 
LinkedIn
News
[June 2024] FaceLift is accepted by ICCV 2025. See you in Honolulu, Hawaii!
[May 2024] Return to Adobe Research as a research intern.
[May 2024] Check out InstaInpaint , our method for 3D scene inpainting within 0.4 seconds.
[May 2024] Check out HoliGS , embodied 4D view synthesis from a long monocular RGB video.
Research Experience
Adobe Research Research Intern May 2024 - Present
University of California, Merced Research Assistant Aug. 2023 - Present
University of Illinois, Urbana-Champaign Research Assistant Aug. 2021 - May 2023
University of California, Berkeley Undergraduate Researcher Jan. 2020 - Aug. 2020
ShanghaiTech University Undergraduate Researcher May 2020 - July 2021
Publications and Preprints
Your browser does not support the video tag.
FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads
Weijie Lyu , Yi Zhou, Ming-Hsuan Yang, Zhixin Shu
ICCV 2025
Project Page /
arXiv /
GitHub
Your browser does not support the video tag.
InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model
Junqi You, Chieh Hubert Lin, Weijie Lyu , Zhengbo Zhang, Ming-Hsuan Yang
arXiv 2025
Project Page /
arXiv /
GitHub
HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis
Xiaoyuan Wang, Yizhou Zhao, Botao Ye, Xiaojun Shan, Weijie Lyu , Lu Qi, Kelvin C.K. Chan, Yinxiao Li, Ming-Hsuan Yang
arXiv 2025
arXiv
Your browser does not support the video tag.
Gaga: Group Any Gaussians via 3D-aware Memory Bank
Weijie Lyu , Xueting Li, Abhijit Kundu, Yi-Hsuan Tsai, Ming-Hsuan Yang
arXiv 2024
Project Page /
arXiv /
GitHub
PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection
Kuan-Chih Huang, Weijie Lyu , Ming-Hsuan Yang, Yi-Hsuan Tsai
CVPR 2024
Paper /
arXiv /
GitHub
Continual Learning in Open-vocabulary Classification with Complementary Memory Systems
Zhen Zhu*, Weijie Lyu* , Yao Xiao, Derek Hoiem
TMLR 2024
arXiv /
GitHub
Consistent Multimodal Generation via A Unified GAN Framework
Zhen Zhu, Yijun Li, Weijie Lyu , Krishna Kumar Singh, Zhixin Shu, Sören Pirk, Derek Hoiem
WACV 2024
Paper /
arXiv /
GitHub
SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles
Chejian Xu*, Wenhao Ding*, Weijie Lyu , Zuxin Liu, Shuai Wang, Yihan He, Hanjiang Hu, Ding Zhao, Bo Li
NeurIPS 2022
Project Page /
Paper /
arXiv /
GitHub
CircuitBot: Learning to Survive with Robotic Circuit Drawing
Xianglong Tan, Weijie Lyu , Andre Rosendo
PLOS ONE 2022
Paper
Academic Services
Conference Reviewer: CVPR, ICCV, ICLR, NeurIPS, Eurographics, ACCV, etc.
Journal Reviewer: TPAMI, TMLR, etc.