CV

Education

The University of Hong Kong, CVMI Lab, Hong Kong (SAR)

Ph.D Student, Dept. of Electrical and Electronic Engineering Aug. 2022 - Present
Advisor: Xiaojuan Qi

Sun Yat-sen University, Guangzhou, China

B.Sc in Mathematics and Applied Mathematics Aug. 2016 - June 2021

GPA: 94/100; Ranking: 2/130
After studying in the School of Physics from Aug. 2016 to June 2017, my interests led me to Mathematics. I ranked first in the transfer exam, enabling my switch to the School of Mathematics, where I completed my degree from Aug. 2017 to June 2021.

University of California, Berkeley CA, USA

Berkeley International Study Program Aug. 2019 - Dec. 2019

Publications

ObjectMover: Generative Object Movement with Video Prior
Xin Yu, Tianyu Wang, Soo Ye Kim, Paul Guerrero, Xi Chen, Qing Liu, Zhe Lin, Xiaojuan Qi.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
TEXGen: a Generative Diffusion Model for Mesh Textures
Xin Yu, Ze Yuan, Yuanchen Guo, Yingtian Liu, Jianhui Liu, Yangguang Li, Yanpei Cao, Ding Liang, Xiaojuan Qi.
ACM SIGGRAPH Asia Conference Proceedings (SIGGRAPH Asia), 2024
Unidream: Unifying diffusion priors for relightable text-to-3d generation
Zexiang Liu, Youtian Lin, Yangguang Li, Xin Yu, Sida Peng, Yanpei Cao, Xiaojuan Qi, Xiaoshui Huang, Ding Liang, Wanli Ouyang.
European Conference on Computer Vision (ECCV), 2024
Text-to-3D with Classifier Score Distillation
Xin Yu, Yuanchen Guo, Yangguang Li, Ding Liang, Songhai Zhang, Xiaojuan Qi.
International Conference on Learning Representations (ICLR), 2024
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
Wenbo Li, Xin Yu, Kun Zhou, Yibing Song, Zhe Lin, Jiaya Jia.
International Conference on Learning Representations (ICLR, Spotlight), 2024
Texture Generation on 3D Meshes with Point-UV Diffusion
Xin Yu, Peng Dai, Wenbo Li, Lan Ma, Zhengze Liu, Xiaojuan Qi.
International Conference on Computer Vision (ICCV, Oral), 2023
Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
Xin Yu, Peng Dai, Wenbo Li, Lan Ma, Jiajun Shen, Jia Li, Xiaojuan Qi.
European Conference on Computer Vision (ECCV), 2022
Is synthetic data from generative models ready for image recognition?
Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Bai Song, Xiaojuan Qi.
International Conference on Learning Representations (ICLR, Spotlight), 2023
Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur
Peng Dai, Yinda Zhang, Xin Yu, Xiaoyang Lyu, Xiaojuan Qi.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Video Demoireing with Relation-Based Temporal Consistency
Peng Dai, Xin Yu, Lan Ma, Baoheng Zhang, Jia Li, Wenbo Li, Jiajun Shen, Xiaojuan Qi.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
High-dimensional anticounterfeiting nanodiamonds authenticated with deep metric learning
Lingzhi Wang*, Xin Yu*, Tongtong Zhang, Yong Hou, Dangyuan Lei, Xiaojuan Qi, Zhiqing Chu.
Nature Communications 2024, *equal contribution

Research/Work Experiences

Adobe, San Jose, USA

Research Scientist Internship (Generative Image Edit) July. 2024 - Nov. 2024

VAST, Beijing, China

Research Internship (3D Generation, we build Tripo) May. 2023 - May. 2024

The University of Hong Kong, Hong Kong (SAR)

Research Assistant, Dept. of Electrical and Electronic Engineering Sept. 2021 - Aug. 2022

Selected Honors/Awards

Postgraduate Scholarship (PGS) Aug 2022 - Present
Technical Papers Honorable Mention Award for SIGGRAPH Asia 2024 Dec. 2024
Outstanding Graduate in SYSU (Top 5%) July 2021
Excellent Bachelor Thesis in SYSU (Top 5%) June 2021
Superior Excellent Graduate of Yat-sen Honor School June 2021
National Scholarship (×2, Top 2%) Dec. 2019, 2018
The First-Class Scholarship (×3, Top 5%) Dec. 2020, 2019, 2018
First Prize of China Undergraduate Mathematical Contest Nov. 2018
Honorable Mention Prize of Interdisciplinary Contest in Modeling (ICM) Apr. 2018
First Prize of Chinese High School Mathematics League Oct. 2015