Tong WU 吴桐

Tong WU 吴桐

Ph.D. Student

Biography

Tong Wu is a final-year Ph.D. student in Multi-Media Lab(MMLab) at CUHK, supervised by Prof. Dahua Lin. She also works closely with Prof. Ziwei Liu at NTU. She is currently a visiting student researcher in Stanford University, working with Prof. Gordon Wetzstein. She got her bachelor’s degree in the EE Department at Tsinghua University in 2020, working with Prof. Yu Wang and Prof. Jiansheng Chen. Her research interests include but not limited to 3D Generation and Reconstruction.

News

Experience

 
 
 
 
 
Visiting Student Researcher
Stanford University
Jan 2024 – Present
 
 
 
 
 
Ph.D. Student at MMLab@CUHK
The Chinese University of Hong Kong
Aug 2020 – Present Hong Kong, China
 
 
 
 
 
Bachelor Degree in Engineering
Tsinghua University
Aug 2016 – Jun 2020 Beijing, China

Publications

GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
CVPR, 2024
Tong Wu*, Guandao Yang*, Zhibing Li*, Kai Zhang, Ziwei Liu, Dahua Lin, Gordon Wetzstein
PDF Cite Code Project
GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
CVPR, 2024
Zeyi Sun*, Ye Fang*, Tong Wu, Pan Zhang, Yuhang Zang, Shu Kong, Yuanjun Xiong, Dahua Lin, Jiaqi Wang
PDF Cite Code Project
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
GPT4Point: A Unified Framework for Point-Language Understanding and Generation
CVPR, 2024
Zhangyang Qi*, Ye Fang*, Zeyi Sun*, Xiaoyang Wu, Tong Wu, Jiaqi Wang#, Dahua Lin, Hengshuang Zhao#
PDF Cite Code Project
GPT4Point: A Unified Framework for Point-Language Understanding and Generation
Large-vocabulary 3d diffusion model with transformer
ICLR, 2024
Ziang Cao, Fangzhou Hong, Tong Wu, Liang Pan, Ziwei Liu
PDF Cite Code Project
Large-vocabulary 3d diffusion model with transformer
HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
SIGGRAPH Asia, 2023, conference track
Tong Wu*, Zhibing Li*, Shuai Yang*, Pan Zhang, Xingang Pan, Jiaqi Wang, Ziwei Liu, Dahua Lin
Cite Project
HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
CVPR, 2023 Best Paper Award Candidate, Top 12/9155
Tong Wu, Jiarui Zhang, Xiao Fu, Yuxin Wang, Jiawei Ren, Liang Pan, Wayne Wu, Lei Yang, Jiaqi Wang, Chen Qian, Dahua Lin, Ziwei Liu
PDF Cite Code Project
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
V3Det: Vast Vocabulary Visual Detection Dataset
ICCV, 2023 Oral presentation
Jiaqi Wang*, Pan Zhang*, Tao Chu*, Yuhang Cao*, Yujie Zhou, Tong Wu, Bin Wang, Conghui He, Dahua Lin
PDF Cite Code Project
V3Det: Vast Vocabulary Visual Detection Dataset
Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
ICLR, 2023 Spotlight
Tong Wu, Jiaqi Wang, Xingang Pan, Xudong Xu, Christian Theobalt, Ziwei Liu, Dahua Lin
PDF Cite Code
Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion
NeurIPS, 2021
Tong Wu, Liang Pan, Junzhe Zhang, Tai Wang, Ziwei Liu, Dahua Lin
PDF Cite Code
Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion
Few-Shot Object Detection via Association and DIscrimination
NeurIPS, 2021
Yuhang Cao, Jiaqi Wang, Ying Jin, Tong Wu, Kai Chen, Ziwei Liu, Dahua Lin
PDF Cite Code
Few-Shot Object Detection via Association and DIscrimination
Adversarial Robustness under Long-Tailed Distribution
CVPR, 2021 Oral presentation
Tong Wu, Ziwei Liu, Qingqiu Huang, Yu Wang, Dahua Lin
PDF Cite Code
Adversarial Robustness under Long-Tailed Distribution
Towards Evaluating and Training Verifiably Robust Neural Networks
CVPR, 2021 Oral presentation
Zhaoyang Lyu, Minghao Guo, Tong Wu, Guodong Xu, Dahua Lin
PDF Cite Code
Towards Evaluating and Training Verifiably Robust Neural Networks
Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification
TPAMI, 2022
Weitao Wan, Jiansheng Chen, Cheng Yu, Tong Wu, Yuanyi Zhong, Ming-Hsuan Yang
PDF Cite
Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
ECCV, 2020 Spotlight
Tong Wu, Qingqiu Huang, Ziwei Liu, Yu Wang, Dahua Lin
PDF Cite Code
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation
ECCV, 2020
Qingqiu Huang, Lei Yang, Huaiyi Huang, Tong Wu, Dahua Lin
PDF Cite Project
Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation
Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
Technique report, 2020
Tong Wu, Xuefei Ning, Wenshuo Li, Ranran Huang, Huazhong Yang, Yu Wang
PDF Cite
Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
Visual-friendly Aesthetic QR Code Generation using Image Style Transfer
Technique report, 2019
Tong Wu, Jiansheng Chen, Yiqing Huang, Yu Wang
PDF Cite
Visual-friendly Aesthetic QR Code Generation using Image Style Transfer

Honors and Awards

  • CVPR 2023 Award Candidate, 2023
  • Hong Kong PhD Fellowship Scheme (HKPFS) of Hong Kong, 2020
  • Outstanding Graduate of Beijing, 2020
  • Outstanding Graduate of Tsinghua University, 2020
  • Outstanding Graduation Paper of Tsinghua University, 2020
  • National Scholarship, 2018
  • Three times Annual Scholarship for Academic Excellence by Tsinghua University, 2017-2019
  • First Prize for National Physical Competition for College Students in China, 2017