xiaoyang

Xiaoyang Wu

Ph.D Student

Department of Computer Science

The University of Hong Kong

Email: [email protected]

Biography

I am a second-year Ph.D student in the Department of Computer Science, The University of Hong Kong (HKU), supervised by Dr. Hengshuang Zhao. Before that, I obtained a Bachelor of Science in Mathematics from Sun Yat-sen University, supervised by Dr. Guanbin Li.

Currently, I am also a research scientist intern with The Surreal team at Meta's Reality Labs, working with Dr. Julian Straub on large-scale pre-training technology for 3D perception. Before that, I have spent wonderful times as an intern with Dr. Kaicheng Yu at Alibaba, and Prof. Wanli Ouyang at Shanghai AI Lab.

My long-term aspiration is to create innovations that might change human life. With this vision in mind, I have embarked on a journey in the realm of 3D, a data modality that extends beyond traditional human perception. My current research interests and focus are on developing a unified representation system for 3D perception, reconstruction, and interaction. I hope my research efforts can contribute to future applications related to spatial intelligence. More experiences about me please refer to my publications and my Google Scholar. Reach out to me over email for discussion or any opportunities.

News

Awards

Projects

pointcept
sam3d

SAM3D: Segment Anything in 3D Scenes
Yunhan Yang, Xiaoyang Wu, Tong He, Hengshuang Zhao, Xihui Liu
[Report] [Code] [Bib] - SAM3D

Publications

CVPR 2024 Oral
ptv3

Point Transformer V3: Simpler, Faster, Stronger
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao
Computer Vision and Pattern Recognition (CVPR) 2024 - Oral (0.78% acceptance rate)
Ranked 1st Place on 2024 Waymo Open Dataset Challenge in Semantic Segmentation
[Paper] [Code] [Bib] [Cert.] - Pointcept Pointcept PTv3

CVPR 2024
msc

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao
Computer Vision and Pattern Recognition (CVPR) 2024
[Paper] [Code] [Bib] - Pointcept Pointcept

CVPR 2024
oacnns

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
Bohao Peng, Xiaoyang Wu, Li Jiang, Yukang Chen, Hengshuang Zhao, Zhuotao Tian, Jiaya Jia
Computer Vision and Pattern Recognition (CVPR) 2024
[Paper] [Code] [Bib] - Pointcept Pointcept

CVPR 2024
gc

GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
Chengyao Wang, Li Jiang, Xiaoyang Wu, Zhuotao Tian, Bohao Peng, Hengshuang Zhao, Jiaya Jia
Computer Vision and Pattern Recognition (CVPR) 2024
[Paper] [Code] [Bib] - Pointcept Pointcept

CVPR 2024
dreamcomposer

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
Yunhan Yang, Yukun Huang, Xiaoyang Wu, Yuan-Chen Guo, Song-Hai Zhang, Hengshuang Zhao, Tong He, Xihui Liu
Computer Vision and Pattern Recognition (CVPR) 2024
[Paper] [Code] [Bib]

CVPR 2024 Highlight
gpt4point

GPT4Point: A Unified Framework for Point-Language Understanding and Generation
Zhangyang Qi, Ye Fang, Zeyi Sun, Xiaoyang Wu, Tong Wu, Jiaqi Wang, Dahua Lin, Hengshuang Zhao
Computer Vision and Pattern Recognition (CVPR) 2024 - Hightlight (2.8% acceptance rate)
[Paper] [Code] [Bib] - Pointcept

CVPR 2024
unipad

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
Honghui Yang, Sha Zhang, Di Huang, Xiaoyang Wu, Haoyi Zhu, Tong He, Shixiang Tang, Hengshuang Zhao, Qibo Qiu, Binbin Lin, Xiaofei He, Wanli Ouyang
Computer Vision and Pattern Recognition (CVPR) 2024
[Paper] [Code] [Bib]

CVPR 2023
msc

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning
Xiaoyang Wu, Xin Wen, Xihui Liu, Hengshuang Zhao
Computer Vision and Pattern Recognition (CVPR) 2023
[Paper] [Code] [Bib] - Pointcept Pointcept

CVPR 2023 Highlight
hdmnet

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chengyao Wang, Shu Liu, Jingyong Su, Jiaya Jia
Computer Vision and Pattern Recognition (CVPR) 2023 - Hightlight (2.5% acceptance rate)
[Paper] [Code] [Bib]

CVPR 2023
mars3d

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds
Jiahui Liu*, Chirui Chang*, Jianhui Liu, Xiaoyang Wu, Lan Ma, Xiaojuan Qi
Computer Vision and Pattern Recognition (CVPR) 2023
[Paper] [Code] [Bib]

CVPR 2023
ceco

Understanding Imbalanced Semantic Segmentation Through Neural Collapse
Zhisheng Zhong*, Jiequan Cui*, Yibo Yang*, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia
Computer Vision and Pattern Recognition (CVPR) 2023
[Paper] [Code] [Bib] - Pointcept Pointcept

NeurIPS 2022
ptv2

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao
Neural Information Processing Systems (NeurIPS) 2022
[Paper] [Code] [Bib] - Pointcept Pointcept

Experiences

The University of Hong Kong

Ph.D Student, Computer Science, 2022 ~ 2026

The University of California, Berkeley

Exchange Student, 2018 ~ 2019

Sun Yet-sen University

B.S, Mathematics, 2016 ~ 2021

Activities