Tsinghua University BNRist

Email:

taijiang@tsinghua.edu.cn.

Addr.:

Rm. 9-207, East Main Bldg., Tsinghua University, Beijing 100084, China.


 

ABOUT ME

 

I am an assistant researcher of the Graphics and Geometric Computing Group in the Department of Computer Science and Technology at Tsinghua University, Beijing, P. R. China.

 

 

I received my bachelor's degree and Ph.D., mentored by Prof. Shi-Min Hu, in Computer Science and Technology from Tsinghua University in 2011 and 2016, respectively.

 

 

My research interests are in computer graphics. Currently I'm working on:

-visual media learning

-SLAM and 3D reconstruction

-human robot interaction.

 


 

PUBLICATIONS (SELECTED)

Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

 

Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu, Shi-Min Hu.

 

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), Accepted, 2022.

 

PAPER[arXiv]   Code  

 

Recursive-NeRF: An Efficient and Dynamically Growing NeRF

 

Guo-Wei Yang, Wen-Yang Zhou, Hao-Yang Peng, Dun Liang, Tai-Jiang Mu, Shi-Min Hu.

 

IEEE Transactions on Visualization and Computer Graphics (TVCG), Accepted, 2022.

 

PAPER[arXiv]   Code  

 

CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene

 

Hao-Xiang Chen, Jiahui Huang, Tai-Jiang Mu*, Shi-Min Hu.

 

Proceedings of the European Conference on Computer Vision (ECCV) 2022, accepted.

 

PAPER  [arXiv]   Code [coming soon]

 

ObjectFusion: Accurate Object-level SLAM with Neural Object Priors

 

Zi-Xin Zou, Shi-Sheng Huang, Tai-Jiang Mu*, Yu-Ping Wang.

 

Graphical Models 2022, Volume 123, 101165.

 

PAPER

 

ClusterGNN: Cluster-Based Coarse-To-Fine Graph Neural Network for Efficient Feature Matching

 

Yan Shi, Jun-Xiong Cai, Yoli Shavit, Tai-Jiang Mu, Wensen Feng, Kai Zhang.

 

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 12517-12526, 2022.

 

PAPER  [arXiv]

 

Subdivision-Based Mesh Convolution Networks

 

Shi-Min Hu, Zheng-Ning Liu, Meng-Hao Guo, Jun-Xiong Cai, Jiahui Huang, Tai-Jiang Tai, Ralph R. Martin.

 

ACM Transactions on Graphics (TOG) 41(3): 25:1-25:16 (2022)

 

PAPER   Code  

 

Accurate Dynamic SLAM Using CRF-Based Long-Term Consistency

 

Zheng-Jun Du, Shi-Sheng Huang, Tai-Jiang Mu*, Qunhe Zhao, Ralph R. Martin and Kun Xu.

 

IEEE Transactions on Visualization and Computer Graphics (TVCG) 28(4): 1745-1757 (2022).

 

PAPER[CVM2020 Version]   Video   Supp   Code

 

Supervoxel Convolution for Online 3D Semantic Segmentation

 

Shi-Sheng Huang, Ze-Yu Ma, Tai-Jiang Mu, Hongbo Fu, Shi-Min Hu.

 

ACM Transactions on Graphics (TOG) 40(3): 34:1-34:15 (2021).

 

PROJECT   PAPER   Video   Supp  

 

PCT: Point Cloud Transformer

 

Meng-Hao Guo, Jun-Xiong Cai, Zheng-Ning Liu, Tai-Jiang Mu, Ralph R. Martin, Shi-Min Hu.

 

Computational Visual Media 7(2): 187-199 (2021)

 

PAPER   Code  

 

ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings

 

Jia-Hui Huang, Sheng Yang, Tai-Jiang Mu and Shi-Min Hu.

 

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2168-2177, 2020.

 

PAPER  

 

Lidar-Monocular Visual Odometry using Point and Line Features

 

Shi-Sheng Huang, Ze-Yu Ma, Tai-Jiang Mu, Hongbo Fu and Shi-Min Hu.

 

Proceedings of the International Conference on Robotics and Automation (ICRA), 1091-1097, 2020.

 

PAPER   Video  

 

S4Net: Single Stage Salient-Instance Segmentation

 

Ruochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang and Shi-Min Hu.

 

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6103-6112, 2019.

 

PAPER   PROJECT   Code

 

A Response Time Model for Abrupt Changes in Binocular Disparity

 

Tai-Jiang Mu, Jia-Jia Sun, Ralph R. Martin, and Shi-Min Hu.

 

The Visual Computer 31(5): 675-687 (2015).

 

PAPER  

 

Stereoscopic Image Completion and Depth Recovery

 

Tai-Jiang Mu, Ju-Hong Wang, Song-Pei Du, and Shi-Min Hu.

 

The Visual Computer 30(6-8): 833-843 (2014).

 

PAPER  

 


Locations of visitors to this page