About me

I am currently a Ph.D. student at Nanjing University of Aeronautics and Astronautics, under the supervision of Qingshan Liu. Previously, I worked as an algorithm engineer at Leapmotor Technology from July 2021 to February 2023. I earned both my Master's and Bachelor's degrees from Nanjing University of Information Science and Technology, also under the guidance of Qingshan Liu. My current research primarily focuses on general 3D perception, including segmentation and detection of point cloud. Here is my personal CV.

News

• [2024/07] SuperFlow was accepted by ECCV 2024.
• [2024/06] Our team, PTv3-EX, secured first place in the 2024 Waymo Open Dataset Challenge.
• [2022/07] Waterfall-Net was accepted by PRCV 2022.
• [2022/04] CED-Net was accepted by Multimedia Systems.
• [2021/12] SA-Net was accepted by ICOMV 2022.
• [2021/04] BAF-LAC was accepted by TIP.

Education

Nanjing University of Aeronautics and Astronautics (NUAA) April 2023 - Present Ph.D. in Computer Science and Technology

Nanjing University of Information Science and Technology (NUIST) September 2018 - June 2021 M.S. in Control Science and Engineering

Nanjing University of Information Science and Technology (NUIST) September 2014 - June 2018 Major: B.E. in Electrical Engineering and Automation

Publications

Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding Lingdong Kong*, Xiang Xu*, Jun Cen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu IEEE/CVF Winter Conference on Applications of Computer Vision, 2025 [Paper]   [Code]

4D Contrastive Superflows are Dense 3D Representation Learners Xiang Xu*, Lingdong Kong*, Hui Shuai, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu, Qingshan Liu European Conference on Computer Vision, 2024 [Paper]   [Code]   [Poster]

Waterfall-Net: Waterfall Feature Aggregation for Point Cloud Semantic Segmentation Hui Shuai, Xiang Xu, Qingshan Liu Chinese Conference on Pattern Recognition and Computer Vision, 2022 [Paper]   [Code]

CED-Net: Contextual Encoder-Decoder Network for 3D Face Reconstruction Lei Zhu, Shanmin Wang, Zengqun Zhao, Xiang Xu, Qingshan Liu Multimedia Systems, 2022 [Paper]

Semantic-Aware Object Detection for 3D Point Cloud Xiang Xu, Gang Huang, Laifeng Hu, Yaonong Wang International Conference on Optics and Machine Vision, 2022 [Paper]

Backward Attentive Fusing Network with Local Aggregation Classifier for 3D Point Cloud Semantic Segmentation Hui Shuai, Xiang Xu, Qingshan Liu IEEE Transactions on Image Processing 2021 [Paper]   [Code]

Preprints

An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models Jiahao Sun, Chunmei Qing, Xiang Xu, Lingdong Kong, Youquan Liu, Li Li, Chenming Zhu, Jingwei Zhang, Zeqi Xiao, Runnan Chen, Tai Wang, Wenwei Zhang, Kai Chen arXiv 2024 [Paper]   [Code]

Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving Lingdong Kong, Xiang Xu, Jiawei Ren, Wenwei Zhang, Liang Pan, Kai Chen, Wei Tsang Ooi, Ziwei Liu arXiv 2024 [Paper]   [Code]

FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation Xiang Xu, Lingdong Kong, Hui Shuai, Qingshan Liu arXiv 2024 [Paper]   [Code]   [Project]   [Demo]

Research Projects

MMDetection3D: OpenMMLab Next-Generation Platform for General 3D Object Detection MMDetection3D Contributors January 2023 - Present [Code]   [Docs]

Experience

Leapmotor Technologies Co. Ltd. July 2021 - February 2023. Advisor: Laifeng Hu Focus: Lidar perception for autonomous driving.

Miscellaneous

Academic Services
I collaborated on MMDetection3D, working closely with Wenwei Zhang and Lingdong Kong.
I served as a reviewer for PRCV.

Hobbies
Love: 🏀Basketball, 🎶music, 🏸badminton, and 🏓table tennis.