安培,华中农业大学信息学院,副研究员。博士毕业于华中科技大学,主持国家自然科学基金青年基金1项、博士后面上项目1项、重点研发计划子课题1项、国家资助博士后研究人员计划1项、以及校级博士后特别资助1项,以第一作者(含共同第一作者)在CCF/CAAI-A类推荐期刊和会议上发表论文9篇,包括IJCV/CVPR/ICCV/ECCV/T-MM/AAAI/IJCAI。长期从事三维计算机视觉的图像-点云配准机制(Image-to-Point-Cloud Registration, I2P)研究,解决空间定位、三维重建、四维重建中的关键问题,构建课题研究与作物育种、动物表型分析的应用关联。部分论文代码开源于https://github.com/anpei96/。
培养原则:
回归问题本身、鼓励代码开源、重视效果呈现、不唯论文等级(能解决问题就是好工作)
研究方向:
图像-点云配准及其在表型分析中的应用
主要工作:
[26-01] Pei An, Junfeng Ding, Jiaqi Yang*, Yulong Wang, Liangliang Nan*, and et al. Hg-I2P: Bridging modalities for generalizable image-to-point-cloud registration via heterogeneous graphs, in Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), 2026, 39042-39051. CCF-A会议 图像-点云配准中的特征匹配——拓扑异构图视角,是[25-02]工作的升级
[26-02] Pei An, Muyao Peng, Junfeng Ding, Jiaqi Yang* and Liangliang Nan*. Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration, in Proceedings of European Conference on Computer Vision (ECCV), 2026, 583-600. CAAI-A会议 图像-点云配准中的误匹配消除——增广兼容图模型
[26-03] Pei An, Jiaqi Yang, Yulong Wang, Siwen Quan* and Liangliang Nan*. OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration, in Proceedings of European Conference on Computer Vision (ECCV), 2026, 258-275. CAAI-A会议 图像-点云配准中的互注意力再探——微分方程视角
[26-04] Siwen Quan, Junhao Yu, Ziming Nie, Muze Wang, Sijia Feng, Pei An*(共同通讯), and Jiaqi Yang*. Deep learning for geometric 3D point cloud enhancement: A survey. Computational Visual Media, 2026, 1-54. CCF-B/中科院1区 点云几何增强综述——去噪、补全、超分
[25-01] Pei An, Jiaqi Yang, You Yang*, and et al. MinCD-PnP: Learning 2D-3D Correspondences with Approximate Blind PnP, in Proceedings of International Conference on Computer Vision (ICCV), 2025, 26519-26528. CCF-A会议 图像-点云配准中的特征监督学习——Blind PnP优化视角
[25-02] Pei An, Jiaqi Yang, Jie Ma, You Yang*, and et al. Top-I2P: Explore Open-Domain Image-to-Point Cloud Registration using Topology Relationships, in Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2025, 674-683. CAAI-A会议(Oral) 图像-点云配准中的特征匹配——拓扑关系视角
[25-03] Pei An, You Yang*, Jiaqi Yang, and et al. Enhance Image-to-Point-Cloud Registration with Beltrami Flow. International Journal of Computer Vision (IJCV), 2025, 133(12): 8589-8616. CCF-A期刊 图像-点云配准中的特征交互——流形上的Beltrami flow方法
[25-04] Yijie Zhang, Pei An, Zhilong Li, Song Hu, Qiong Liu, and You Yang. Light field-guided optical synthetic aperture imaging system on master–slave UAVs, Journal of the Optical Society of America A, 42, 1551-1563 中科院4区 图像-点云配准应用——无人机蜂群光学成像
[25-05] Junfeng Ding, Pei An*, and et al. An Efficient and Accurate UAV State Estimation Method with Multi-LiDAR–IMU–Camera Fusion. Drones 2025, 9: 823-846. 中科院3区 图像-点云配准应用——无人机多传感器融合SLAM
[24-01] Pei An, Jie Ma*, You Yang*, and et al. ESC-Net: Alleviating triple sparsity on 3D LiDAR point clouds for extreme sparse scene completion, IEEE Transactions on Multimedia, 2024, 26: 6799-6810. CCF-A期刊 激光雷达的稀疏点云补全——多重稀疏性切入
[24-02] Pei An, Jie Ma*, You Yang*, and et al. SP-Det: Leveraging saliency prediction for voxel-based 3D object detection in sparse point cloud, IEEE Transactions on Multimedia, 2023, 26(1): 2795-2808. CCF-A期刊 激光雷达的稀疏点云目标检测——点云显著性切入
[24-03] Pei An, Jie Ma*, You Yang*, and et al. OL-Reg: Registration of image and sparse LiDAR point cloud with object-level dense correspondences. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34: 7523-7536. CCF-B/中科院1区 交通场景下的图像-点云配准——投影ICP方法,是[20-02]工作的升级
[24-04] Pei An, Jie Ma*, You Yang*, and et al. Survey of Extrinsic Calibration on LiDAR-Camera System for Intelligent Vehicle: Challenges, Approaches, and Trends. IEEE Transactions on Intelligent Transportation Systems, 2024, 25: 15342-15366. CCF-B/中科院1区 图像-点云配准方法综述——以相机-激光雷达标定为例
[23-01] Pei An, Jie Ma*, You Yang*, and et al. RS-Aug: Improve 3D object detection on LiDAR with realistic simulator based data augmentation, IEEE Transactions on Intelligent Transportation Systems, 2023, 24(9): 10165-10176. CCF-B/中科院1区 激光雷达点云仿真及其在目标检测应用
[22-01] Pei An, Jie Ma*, and et al. Deep structural information fusion for 3D object detection on LiDAR-camera system. Computer Vision and Image Understanding, 2022, 214: 295-307. CCF-B/中科院3区 图像-点云融合三维目标检测
[22-02] Junxiong Liang, Pei An(共同一作), Jie Ma. Distribution Aware VoteNet for 3D Object Detection, in Proceeding of Association for the Advancement of Artificial Intelligence (AAAI), 2022, 1583-1591. CCF-A会议 稀疏点云的三维目标检测
[22-03] Pei An, Wenxing Fu*, Jie Ma and et al. Lambertian model based normal guided depth completion for LiDAR-camera system, IEEE Geoscience and Remote Sensing Letters, 2022, 19:1-5. 中科院3区 图像引导点云补全——朗伯体成像视角
[21-01] Pei An, Jie Ma, Jun Zhang*, and et al. Two-point calibration method for a zoom camera with an approximate focal-invariant radial distortion model. Journal of the Optical Society of America A, 2021, 38: 504-514. 中科院4区 图像-点云配准中的位姿解算——P2P情形
[20-01] Pei An, Jie Ma*, and et al. Geometric calibration for LiDAR-camera system fusing 3D-2D and 3D-3D point correspondences. Optics Express, 2020, 28: 18261-18282. 中科院2区 传感器标定中的图像-点云配准——主-辅标定物方法
[20-02] Pei An, Jie Ma*, and et al. LiDAR-camera system extrinsic calibration by establishing virtual point correspondences from pseudo calibration objects. Optics Express, 2020, 28: 2122-2141. 中科院2区 传感器标定中的图像-点云配准——以前景物体为参考
科研项目:
[25-1] 国家自然科学基金青年科学基金项目C档,拓扑关系下的图像-点云配准方法研究,30万,2025 (主持)
[25-2] 国家资助博士后研究人员计划C档,异构图视角下的图像-点云配准方法研究,2025 (主持)
[24-1] 中国博士后科学基金面上项目,面向长期视觉定位的图像-点云配准方法研究, 8万, 2024 (主持)
[24-2] 华中科技大学博士后特别资助计划,面向开放场景的图像-点云配准研究, 16万, 2024 (主持)
[24-3] 国家重点研发计划子课题,面向应急场景的多模态信息协同融合技术, 25万, 2024 (主持)
[24-4] 湖北省重点研发计划, 基于蜂群的应急态势感知与信息融合关键技术研发, 100万, 2024 (核心参与)
[24-5] 多谱信息智能处理国家重点实验室开放基金, 动态复杂场景下三维点云目标检测与跟踪技术研究, 40万, 2024 (核心参与)
