
敖晟,博士,现为厦门大学信息学院计算机科学与技术系助理教授。2024年师从郭裕兰教授获得中山大学工学博士学位。
主要研究方向为三维点云处理。近五年来,以第一作者/通讯作者身份在CCF-A类期刊和会议上发表5篇论文,包括IEEE TPAMI和CVPR。2篇论文分别获评2022年深圳市第二届优秀科技学术论文、2023年深圳市第三届优秀科技学术论文。博士学位论文获评2024年度深圳市人工智能学会优秀博士学位论文。获授权国家发明专利6项,曾担任IEEE TPAMI、TIP、CVPR、ICCV等国际顶级期刊及会议审稿人。
招收硕士生和对科研感兴趣的高年级本科生,欢迎对三维视觉以及相关领域有兴趣的同学联系我。更多科研论文信息请查看个人主页:
https://aosheng1996.github.io/
【代表性论文】 (*Equal contribution, †Corresponding author)
[1] Sheng Ao, Yulan Guo, Yingying Hu, Bo Yang, Andrew Markham, Zengping Chen. You Only Train Once: Learning General and Distinctive 3D Local Descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI). 45(3): 3949-3967, 2023. (CCF-A,TOP期刊,影响因子:20.6)
[2] Sheng Ao, Qingyong Hu, Bo Yang, Andrew Markham, Yulan Guo. SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration. IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), June 19-25, 1-12, Virtual, 2021. (CCF-A,TOP会议)
[3] Sheng Ao, Qingyong Hu, Hanyun Wang, Kai Xu, Yulan Guo. BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration. IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), June 18-22, Vancouver, Canada, 2023. (CCF-A,TOP会议)
[4] Guiyu Zhao*, Sheng Ao*, Ye Zhang, Kai Xu, Yulan Guo. Progressive Correspondence Regenerator for Robust 3D Registration. IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), June 11-15, Nash-ville , USA, 2025. (CCF-A,TOP会议)
[5] Yongshu Huang, Chen Liu, Minghang Zhu, Sheng Ao†, Chenglu Wen, Cheng Wang†. DiffLO: Semantic-Aware LiDAR Odometry with Diffusion-Based Refinement. IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), June 11-15, Nashville , USA, 2025. (CCF-A,TOP会议)
[6] Sheng Ao, Yulan Guo, Jindong Tian, Yong Tian, Dong Li. A Repeatable and Robust Local Reference Frame for 3D Surface Matching. Pattern Recognition (PR), 2020, 100: 107186. (CCF-B,中科院SCI-1区)
[7] Yixin Zhang*, Sheng Ao*, Qingyong Hu, Tao Chang, Yulan Guo. U2Frame: A Unified and Unsupervised Learning Framework for LiDAR-based Loop Closing. IEEE International Conference on Robotics and Automation (ICRA), May 19–23, Atlanta, USA, 2025. (清华A类,TOP会议)