CV

Education

• Ph.D. in Artificial Intelligence, Xiamen University, 2024 - Present
• B.Sc. in Computer Science and Technology, Xiamen University, 2020 - 2024

Research Experience

• 2024 - Present: Graduate Student
  • ASC Laboratory, Xiamen University
  • Research focus: 3D Computer Vision, Point Cloud Registration
• 2023 - 2024: Undergraduate Student
  • ASC Laboratory, Xiamen University
  • Research projects on cross-source and unsupervised point cloud registration
  • Contributed to top-tier conference publications (AAAI, NeurIPS, CVPR, ECCV)

Skills

• Programming Languages: Python, C++
• Deep Learning Frameworks: PyTorch, Triton
• 3D Processing Libraries: Open3D, PCL (Point Cloud Library)
• Research Areas:
  • Point Cloud Registration
  • 3D Computer Vision
  • Unsupervised Learning
  • Cross-modal Learning

Publications

MoT3DVG: A Benchmark for Outdoor 3D Visual Grounding with Motion-Aware Descriptions and Temporal Cues

Coming Soon

Cross-Modal Prior-Guided Training with Visual Foundation Models for Unsupervised LiDAR Point Cloud Registration

Coming Soon

Unsupervised Point Cloud Registration via Training-Time Semantic Guidance

Xiong, K., Xu, S., Ao, S., Shen, S., Wang, C., Wen, C. (2026). Unsupervised Point Cloud Registration via Training-Time Semantic Guidance. In: Favaro, P., Kukelova, Z., Maki, A., Rohrbach, A., Schindler, K., Tombari, F. (eds) Computer Vision – ECCV 2026. ECCV 2026. Lecture Notes in Computer Science, vol 17035. Springer, Cham. https://doi.org/10.1007/978-3-032-37464-6_26

TACO: Task-Aware Contrastive Learning for Joint LiDAR Localization and 3D Object Detection

Leyuan, Xing, et al. "TACO: Task-Aware Contrastive Learning for Joint LiDAR Localization and 3D Object Detection", In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration

Xiong, Kezheng, et al. "Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration." The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024).

SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration

Xiong, Kezheng, et al. "SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38. No. 6. 2024.

Teaching

Data Structures (Teaching Assistant)

Datasets

• KITTI CrossSource Dataset: A large-scale cross-source point cloud dataset for benchmarking registration methods
  • Released as part of SPEAL work (AAAI 2024)
  • Available at: https://github.com/kezheng1204/KITTI-CrossSource/

Honors and Awards

Currently no honors or awards to display.