About me

I am a Ph.D. student of MMLab (Multimedia Laboratory), The Chinese University of Hong Kong, supervised by Dahua Lin. Previously I spent four wonderful years and obtained my Bachelor’s Degree at Zhejiang University. I am excited about all the vision or AI technologies that can change people’s lifestyles, for example, building intelligent agents that can interact with us. My current research is mainly focused on general 3D perception, including different modalities, tasks and scenarios. I am also interested in other extensive 3D vision research and their robotic applications.

News

Education

cuhk
 The Chinese University of Hong Kong (CUHK)
  August 2019 - July 2023 (Expected)
  Ph.D. in Information Engineering
zju
 Zhejiang University (ZJU)
  August 2015 - July 2019
  Major: B.E. in Information Engineering
  Minor: Advanced Honor Class of Engineering Education (ACEE), Chu Kochen Honors College

Publications

Vision-Only 3D Detection
dfm
 Monocular 3D Object Detection with Depth from Motion
  Tai Wang, Jiangmiao Pang, Dahua Lin
  European Conference on Computer Vision (ECCV) 2022, Oral
  [Paper] [Code] [Zhihu] [Bibtex]
mv-fcos3d
 MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection
 with Pretrained Monocular Backbones
  Tai Wang, Qing Lian, Chenming Zhu, Xinge Zhu, Wenwei Zhang
  Runner-up solution in the Waymo Camera-Only 3D detection challenge, CVPR 2022
  [Preliminary Tech Report] [Code] [Bibtex]
pgd
 Probabilistic and Geometric Depth: Detecting Objects in Perspective
  Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin
  Conference on Robot Learning (CoRL) 2021
  [Paper] [Code] [Poster] [Bibtex]
fcos3d
 FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
  Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin
  ICCV Workshop on 3D Object Detection from Images (ICCVW) 2021, Best Paper Award
  1st place solution of vision-only methods in the nuScenes 3D detection challenge, NeurIPS 2020
  [Paper] [Code] [Slides] [Zhihu] [Bibtex]
side
 SIDE: Center-Based Stereo 3D Detector with Structure-Aware
 Instance Depth Estimation
  Xidong Peng, Xinge Zhu, Tai Wang, Yuexin Ma
  IEEE Winter Conference on Applications of Computer Vision (WACV) 2022
  [Paper] [Code] [Bibtex]

Voxel Representation Learning in LiDAR-Based Perception
cylinder3d
 Cylindrical and Asymmetrical 3D Convolution Networks for
 LiDAR Segmentation
  Xinge Zhu*, Hui Zhou*, Tai Wang, Fangzhou Hong, Yuexin Ma, Wei Li, Hongsheng Li, Dahua Lin
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021, Oral
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021
  [Paper] [Code] [TPAMI version] [Bibtex]
reconfig
 Reconfigurable Voxels: A New Representation for LiDAR-Based
 Point Clouds
  Tai Wang, Xinge Zhu, Dahua Lin
  Conference on Robot Learning (CoRL) 2020
  [Paper] [Spotlight Talk] [Bibtex]
ssn
 SSN: Shape Signature Networks for Object Detection from
 Point Clouds
  Xinge Zhu, Yuexin Ma, Tai Wang, Yan Xu, Jianping Shi, Dahua Lin,
  European Conference on Computeer Vision (ECCV) 2020
  [Paper] [Code] [Bibtex]

Efficient Annotation of LiDAR Point Clouds
flava
 FLAVA: Find, Localize, Adjust and Verify to Annotate LiDAR-based
 Point Clouds
  Tai Wang, Conghui He, Zhe Wang, Jianping Shi, Dahua Lin
  ACM Symposium on User Interface Software and Technology (UIST) 2020, Poster
  [Full Tech Report] [Poster] [Poster Summary] [Demo] [Bibtex]

3D Generation and Reconstruction
dcd
 Density-aware Chamfer Distance as a Comprehensive Metric for
 Point Cloud Completion
  Tong Wu, Liang Pan, Junzhe Zhang, Tai Wang, Ziwei Liu, Dahua Lin
  Advances in Neural Information Processing Systems (NeurIPS), 2021
  [Paper] [Code] [Bibtex]

Research Projects

mmdet3d
 MMDetection3D: The Next-Generation Platform for General 3D Detection
  A versatile, open-source 3D object detection toolbox based on PyTorch
  MMDetection3D Contributors
  May 2020 – Now
  [Code] [Doc] [Bibtex]
s2mesh
 Spherical Convolutional Networks for 3D Mesh Processing
  New approaches to generating 3D meshes from scratch with S2 parametrization & extended spherical CNNs
  Tai Wang, Weiwei Zhou and Zicheng Liao
  Under revision and further development
  Mar 2018 – Nov 2018

Experience

shlab
 Visiting Scholar, Shanghai AI Laboratory
  July 2020 - Now.  Advisor: Jiangmiao Pang, Kai Chen
  Focus: The next-generation platform for general 3D perception
sensetime
 Adjunct Researcher, Sensetime
  Nov. 2019 - June 2020.  Advisor: Conghui He, Zhe Wang, Jianping Shi
  Focus: Efficient annotation of LiDAR point clouds, development of LiDAR perception system
cuhk
 Junior Research Assistant, The Chinese University of Hong Kong (CUHK)
  Feb. 2019 - May 2019.  Advisor: Dahua Lin
  Focus: Real-time 3D object detection in autonomous driving
AZFT
 Research Intern, Alibaba-ZJU Joint Institute of Frontier Technologies (AZFT)
  Dec. 2017 - June 2019.  Advisor: Zicheng Liao, Gang Wang. I also worked with Dr. Lechao Cheng.
  Focus: Joint analysis of 2D Images and 3D Shapes with machine learning approaches

Selected Awards

Teaching

  • Computer Vision (Undergraduate Course), Winter 2018 @ ZJU
  • IERG2080: Introduction to Systems Programming, Fall 2020 @ CUHK
  • IERG2470B/ESTR2308: Probability Models and Applications (Elite Students), Spring 2021 @ CUHK

Miscellaneous

Academic Services
I served as a reviewer for CVPR, ICCV, ECCV, NeurIPS, ICLR, CoRL, WACV.

Hobbies
Love: 🏀Basketball (I am a big fan of Stephen Curry and Tracy McGrady), 🎵music/🎤singing and good at 🖌️Chinese calligraphy (learned from MA Liangchen and MA Shanshuang).