Xianzhi Li

李贤芝

Associate Professor

School of Computer Science and Technology
Huazhong University of Science and Technology (华中科技大学)
Wuhan, Hubei Province

Email: xzli [at] hust [dot] edu [dot] cn

Now Looking for!!!

Mphil opening: 3D vision, 3D reconstruction, point cloud processing, etc.

Note: passion in research, hardworking, creative, and well-motivated for high-quality research!

Biography

I am an associate professor at Huazhong University of Science and Technology (HUST). My research interests include 3D vision, computer graphics, point cloud processing, and deep learning. I am dedicated to designing machine learning algorithms for processing, analyzing, and sensing 3D data.

Before joining HUST, I was a post-doctoral fellow at The Chinese University of Hong Kong (CUHK) and Hong Kong Center for Logistics Robotics. I have received my Ph.D. degree from the Department of Computer Science and Engineering, CUHK, supervised by Prof. Pheng-Ann Heng and Prof. Chi-Wing Fu. Before that, I received the M.Sc. from Biomedical Engineering at CUHK in 2015 and B. Eng. from Biomedical Engineering at Sichuan University in 2014.

News

[07/2024] Two papers (Mamba3D & MiniGPT-3D) were accepted by ACM MM 2024.
[05/2024] One paper (point scene instance mesh reconstruction) was accepted by TVCG.
[02/2024] One paper (open world point cloud semantic segmentation) was accepted by CVPR 2024.
[09/2023] One paper (3D few-shot object detection) was accepted by NeurIPS 2023.
[07/2023] One paper (point cloud pre-training) was accepted by TMM.
[05/2023] One paper (knowledge base question answering) was accepted by the Findings of ACL 2023.
[04/2023] One paper (3D point cloud pre-training) was accepted by IJCAI 2023.
[11/2022] Two papers (semantic scene completion and 3D object detection) were accepted by AAAI 2023.
[07/2022] One paper (sim-to-real instance segmentation) was accepted by IROS 2022.
[04/2022] One paper (sign language translation) was accepted by the Findings of NAACL 2022.
[02/2022] One paper (part-aware instance segmentation for industrial bin picking) was accepted by ICRA 2022.
[02/2022] One paper (S2R-Pick for industrial robotic bin picking) was accepted by IEEE Robotics and Automation Letters (RA-L) and also accepted for presentation at ICRA 2022.
[11/2021] One paper (RePCD-Net for point cloud denoising) was accepted by IJCV.
[06/2021] One paper (rotation invariant framework for point cloud analysis) was accepted by TVCG.
[06/2021] One paper (SP-GAN) was accepted by SIGGRAPH 2021.
One paper (Disentangle-PU) was accepted by CVPR 2021.
[23/06/2020] Passed the oral defense and became a Dr.!
One paper (deep normal filtering for mesh denoising) was accepted by TVCG.
One paper (unsupervised distinctive region detection) was accepted by TOG.
One paper (PointAugment) was accepted by CVPR 2020.
Two papers (PU-GAN and deep floor plan recognition) were accepted by ICCV 2019.

Selected Publications [Google Scholar]

	Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model Xu Han, Yuan Tang, Zhaoxuan Wang, Xianzhi Li^†. ACM Multimedia 2024. (^† Corresponding author)
	MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors Yuan Tang, Xu Han, Xianzhi Li^†, Qiao Yu, Yixue Hao, Long Hu, Min Chen. ACM Multimedia 2024. (^† Corresponding author)
	PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation Jinfeng Xu, Siyuan Yang, Xianzhi Li^†, Yuan Tang, Yixue Hao, Long Hu, Min Chen. CVPR 2024. (^† Corresponding author)
	JIMR: Joint Semantic and Geometry Learning for Point Scene Instance Mesh Reconstruction Qiao Yu, Xianzhi Li^†, Yuan Tang, Jinfeng Xu, Long Hu, Yixue Hao, Min Chen. TVCG 2024. (^† Corresponding author)
	Pay More Attention to Relation Exploration for Knowledge Base Question Answering Yong Cao, Xianzhi Li^†, Huiwen Liu, Wen Dai, Shuai Chen, Bin Wang, Min Chen, and Daniel Hershcovich. ACL Findings 2023. (^† Corresponding author)
	Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training Ziyu Guo, Renrui Zhang, Longtian Qiu, Xianzhi Li^†, Pheng-Ann Heng. IJCAI 2023. (^† Corresponding author)
	CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion Jinfeng Xu, Xianzhi Li^†, Yuan Tang, Qiao Yu, Yixue Hao, Long Hu, Min Chen. AAAI 2023. (^† Corresponding author) [code]
	Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data Augmentation Yong Cao, Wei Li, Xianzhi Li, Min Chen, Guangyong Chen, Long Hu, Zhengdao Li, Hwang Kai. NAACL Findings 2022. [code]
	Towards Robust Part-aware Instance Segmentation for Industrial Bin Picking Yidan Feng, Biqi Yang, Xianzhi Li^†, Chi-Wing Fu, Rui Cao, Kai Chen, Qi Dou, Mingqiang Wei, Yun-Hui Liu, and Pheng-Ann Heng. IEEE International Conference on Robotics and Automation (ICRA), 2022. (* Joint first author; ^† Corresponding author)
	A Sim-to-Real Object Recognition and Localization Framework for Industrial Robotic Bin Picking Xianzhi Li, Rui Cao, Yidan Feng, Kai Chen, Biqi Yang, Chi-Wing Fu, Yichuan Li, Qi Dou, Yun-Hui Liu, and Pheng-Ann Heng. IEEE Robotics and Automation Letters (RA-L), 2022. (Also accepted by ICRA 2022.)
	RePCD-Net: Feature-aware Recurrent Point Cloud Denoising Network Honghua Chen, Zeyong Wei, Xianzhi Li, Yabin Xu, Mingqiang Wei, Jun Wang. International Journal of Computer Vision (IJCV), 2022. [code]
	A Rotation-invariant Framework for Deep Point Cloud Analysis Xianzhi Li, Ruihui Li, Guangyong Chen, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng. IEEE Transactions on Visualization and Computer Graphics (TVCG), 2021. [code]
	SP-GAN: Sphere-guided 3D Shape Generation and Manipulation Ruihui Li, Xianzhi Li, Ka-Hei Hui, Chi-Wing Fu. ACM SIGGRAPH, 2021. [code]
	Point Cloud Upsampling via Disentangled Refinement Ruihui Li, Xianzhi Li^†, Pheng-Ann Heng, Chi-Wing Fu. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. (^† Corresponding author) [code]
	DNF-Net: a Deep Normal Filtering Network for Mesh Denoising Xianzhi Li, Ruihui Li, Lei Zhu, Chi-Wing Fu, Pheng-Ann Heng. IEEE Transactions on Visualization and Computer Graphics (TVCG), 2020. [code]
	Unsupervised Detection of Distinctive Regions on 3D Shapes Xianzhi Li, Lequan Yu, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng. ACM Transactions on Graphics (TOG), 2020. [code]
	PointAugment: an Auto-Augmentation Framework for Point Cloud Classification Ruihui Li, Xianzhi Li, Pheng-Ann Heng, Chi-Wing Fu. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. (oral) [code]
	PU-GAN: a Point Cloud Upsampling Adversarial Network Ruihui Li, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng. IEEE International Conference on Computer Vision (ICCV), 2019. [code]
	Deep Floor Plan Recognition using a Multi-task Network with Room-boundary-Guided Attention Zhiliang Zeng, Xianzhi Li, Chi-Wing Fu, Ying-Kin Yu. IEEE International Conference on Computer Vision (ICCV), 2019. [code]
	Non-local Low-rank Normal Filtering for Mesh Denoising Xianzhi Li, Lei Zhu, Chi-Wing Fu, Pheng-Ann Heng Computer Graphics Forum (Pacific Graphics), 2018. [code]
	EC-Net: and Edge-aware Point Set Consolidation Network Lequan Yu, Xianzhi Li*, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng. European Conference on Computer Vision* (ECCV), 2018. (* Joint first author) [project page]
	PU-Net: Point Cloud Upsampling Network Lequan Yu, Xianzhi Li*, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng. IEEE Conference on Computer Vision and Pattern Recognition* (CVPR), 2018. (* Joint first author) [code]

Honors & Awards

Teaching Assistant of Merit, 2018

Biomedical Engineering Scholarship, 2015

Outstanding Graduates of Sichuan University, 2014

National Scholarship in China, 2013

Teaching

2022	春季	计算机视觉
2018-2019	Spring	CSCI 5210 Advanced Topics in Computer Graphics and Visualization
2017-2018	Fall	CSCI3260 Principles of Computer Graphics
2017-2018	Spring	CSCI2100 Data Structure
2016-2017	Fall	CSCI3260 Principles of Computer Graphics