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

profile photo
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
sym

Adobe Research


Research Intern


May 2024 - Present

sym

University of California, Merced

Research Assistant


Aug. 2023 - Present

sym

University of Illinois, Urbana-Champaign

Research Assistant


Aug. 2021 - May 2023

sym

University of California, Berkeley

Undergraduate Researcher

Jan. 2020 - Aug. 2020

sym

ShanghaiTech University


Undergraduate Researcher

May 2020 - July 2021

Publications and Preprints
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 GitHub Stars
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 GitHub Stars
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
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 GitHub Stars
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 GitHub Stars
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 GitHub Stars
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.

 

Updated July 2025. Template from Jon Barron