Tong WU 吴桐

Tong WU 吴桐

PostDoc @ Stanford

Biography

Tong Wu is an incoming PostDoc at Stanford University, working with Prof. Gordon Wetzstein. She obtained her PhD degree in 2024 from Multi-Media Lab(MMLab) at CUHK, under the supervision of Prof. Dahua Lin. She also works closely with Prof. Ziwei Liu at NTU and previously served as a visiting student researcher at Stanford University with Prof. Gordon Wetzstein. She received her bachelor’s degree from the EE Department at Tsinghua University in 2020, where she worked with Prof. Yu Wang and Prof. Jiansheng Chen. Her research interests include 3D Vision and AIGC.

News

Experience

 
 
 
 
 
PostDoc
Stanford University
Jan 2025 – Present California, US
 
 
 
 
 
Visiting Student Researcher
Stanford University
Jan 2024 – Apr 2024 California, US
 
 
 
 
 
Ph.D. Student at MMLab@CUHK
The Chinese University of Hong Kong
Aug 2020 – Oct 2024 Hong Kong, China
 
 
 
 
 
Bachelor Degree in Engineering
Tsinghua University
Aug 2016 – Jun 2020 Beijing, China

Publications

Imagine360: Immersive 360 Video Generation from Perspective Anchor
arXiv, 2024
Jing Tan*, Shuai Yang*, Tong Wu, Jingwen He, Yuwei Guo, Ziwei Liu, Dahua Lin
Cite Code Project
Imagine360: Immersive 360 Video Generation from Perspective Anchor
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
NeurIPS, 2024 (Datasets and Benchmarks Track)
Tong Wu, Yinghao Xu, Ryan Po, Mengchen Zhang, Guandao Yang, Jiaqi Wang, Ziwei Liu, Dahua Lin, Gordon Wetzstein
Cite Code Project
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
arXiv, 2024
Junyan Ye*, Baichuan Zhou*, Zilong Huang, Junan Zhang*, Tianyi Bai, Hengrui Kang, Jun He, Honglin Lin, Zihao Wang, Tong Wu, Zhizheng Wu, Yiping Chen, Dahua Lin, Conghui He, Weijia Li *
PDF Cite Code Project
LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
BroadWay: Boost Your Text-to-Video Generation Model in a Training-free Way
arXiv, 2024
Jiazi Bu*, Pengyang Ling*, Pan Zhang, Tong Wu, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Dahua Lin, Jiaqi Wang
PDF Cite Code Project
BroadWay: Boost Your Text-to-Video Generation Model in a Training-free Way
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
arXiv, 2024
Zhaoxi Chen, Jiaxiang Tang, Yuhao Dong, Ziang Cao, Fangzhou Hong, Yushi Lan, Tengfei Wang, Haozhe Xie, Tong Wu, Shunsuke Saito, Liang Pan, Dahua Lin, Ziwei Liu
PDF Cite Code Project
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation
arXiv, 2024
*Shuai Yang*, Jing Tan*, Mengchen Zhang, Tong Wu, Yixuan Li, Gordon Wetzstein, Ziwei Liu, Dahua Lin
PDF Cite Code Project
LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation
Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images
arXiv, 2024
Zhangyang Qi, Yunhan Yang, Mengchen Zhang, Long Xing, Xiaoyang Wu, Tong Wu, Dahua Lin5, Xihui Liu, Jiaqi Wang, Hengshuang Zhao
PDF Cite Code Project
Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images
Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data
arXiv, 2024
Zeyi Sun, Tong Wu, Pan Zhang, Yuhang Zang, Xiaoyi Dong, Yuanjun Xiong, Dahua Lin, Jiaqi Wang
PDF Cite Code Project
Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data
MotionClone: Training-Free Motion Cloning for Controllable Video Generation
arXiv, 2024
Pengyang Ling*, Jiazi Bu*, Pan Zhang, Xiaoyi Dong, Yuhang Zang, Tong Wu, Huaian Chen, Jiaqi Wang, Yi Jin
PDF Cite Code Project
MotionClone: Training-Free Motion Cloning for Controllable Video Generation
Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
NeurIPS, 2024
Ye Fang*, Zeyi Sun*, Tong Wu, Jiaqi Wang, Ziwei Liu, Gordon Wetzstein, Dahua Lin
PDF Cite Code Project
Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation
ECCV, 2024
Mengchen Zhang, Tong Wu, Tai Wang, Tengfei Wang, Ziwei Liu, Dahua Lin
PDF Cite Code
Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
ECCV, 2024
Yongwei Chen*, Tengfei Wang*, Tong Wu, Xingang Pan, Kui Jia, Ziwei Liu
PDF Cite Project
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
arXiv, 2024
, Fangzhou Hong*, Jiaxiang Tang*, Ziang Cao*, Min Shi*, Tong Wu, Zhaoxi Chen, Shuai Yang, Tengfei Wang, Liang Pan, Dahua Lin, Ziwei Liu
PDF Cite Code
3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
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

  • ECCV 2024 Outstanding Reviewer, 2024
  • 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