温程璐 Chenglu Wen教授，博士生导师，国家级青年人才 Professor详情

科研团队

温程璐 Chenglu Wen
教授，博士生导师，国家级青年人才 Professor
clwen@xmu.edu.cn

人工智能系教授，人工智能研究院双聘教授，国家级青年人才，福建省智慧城市感知与计算重点实验室副主任。主要从事三维视觉、点云智能处理、多模态融合感知、协同感知方面研究。主持国家自然科学基金项目4项等国家级项目。成果发表在IEEE TPAMI、IEEE TGRS、IEEE TITS、ISPRS JPRS等期刊及CVPR、ICCV、ECCV、NeurIPS等人工智能国际会议上。获国际摄影测量与遥感学会ISPRS Otto von Gruber奖(www.isprs.org/society/awards/gruber.aspx)，福建省高等教育教学成果奖特等奖两项，福建省科技进步奖二等奖两项，中国激光雷达青年科技奖，CCF智能汽车青年激励计划，上海市科技进步奖二等奖。担任IEEE Transactions on Intelligent Transportation Systems期刊Senior Editor，IEEE Geoscience and Remote Sensing Letters期刊Associate Editor，ISPRS I/2移动测图技术工作组联合主席，CSIG视觉感知专委会副主任，CSIG厦门会员活动中心执委会主席，CNISDE激光雷达专委会AI先进算法工作组组长等。

主持的科研项目

国家自然科学基金项目，面向复杂空间无人探索的协同主动目标感知方法研究，2026-2029
国家自然科学基金项目，面向城市动态场景三维感知的点云序列弱监督学习，2022-2025
国家自然科学基金项目，联合可测点云/多视角图像的大规模对象标记数据集生成，2018-2021
国家自然科学基金项目，室内移动三维测图点云数据的多元质量评价与修补，2015-2017

Dr. Chenglu Wen is a Professor at the Department of Artificial Intelligence at Xiamen University. She was the deputy head of the Department of Artificial Intelligence. She is mainly engaged in the research of 3D scene perception and understanding, LiDAR point cloud processing, and 3D vision. She has been granted 3 National Natural Science Foundation of China projects. She has published over 100 papers and authorized over ten invention patents. She received the 2022 ISPRS Otto von Gruber Award (www.isprs.org/society/awards/gruber.aspx), the 2020 China LiDAR Youth Science and Technology Award, and Best Paper of the 2017 International Mobile Mapping Technology Conference. She serves as the Senior Editor of IEEE Transactions on Intelligent Transportation Systems, and Associate Editor of IEEE Geoscience and Remote Sensing Letters. She is also the co-chair of ISPRS working group I/2 Mobile Mapping Technology (2022-2026).

News

02/2026, our DOtA++ paper is accepted to IEEE TPAMI
11/2025, three papers are accepted to AAAI 2026
08/2025, our CPD++ paper is accepted to IEEE TPAMI
06/2025, two papers are accepted to ICCV 2025
02/2025, seven papers are accepted to CVPR 2025
01/2025, one paper is accepted to ICLR 2025
12/2024, three papers are accepted to AAAI 2025
11/2024, selected as Senior Editor of IEEE TITS
09/2024, two papers are accepted to NeurIPS 2024
09/2024, our HiSC4D paper is accepted to IEEE TPAMI
07/2024, one paper is accepted to ECCV 2024
02/2024, five papers are accepted to CVPR 2024
12/2023, two papers are accepted to AAAI 2024
07/2023, one paper is accepted to ICCV 2023
02/2023, four papers are accepted to CVPR 2023
11/2022, VirConv-S method ranks No.1(car) on the KITTI 2D, 3D and BEV detection leaderboard
11/2022, VirConvTrack ranks No.1(car) on the KITTI tracking leaderboard
11/2022, our 3D object detection paper TED is accepted to AAAI 2023
09/2022, our CasTrack ranks No.1(car) on the KITTI tracking leaderboard
06/2022, received ISPRS Otto von Gruber Award
05/2022, our TED method ranks No.1(car) on the KITTI 3D detection leaderboard (until 11/2022)
05/2022, our CasA++ method ranks No.1(ped. and cyc.)/No.2(car) on the KITTI 3D detection leaderboard
03/2022, two Lidar motion capture papers are accepted to CVPR 2022
04/2021, two papers are accepted to IJCAI 2021
01/2021, our PC-TCNN ranks No.1(car) on the KITTI tracking leaderboard
11/2020, received CNISDE Lidar Youth Science and Technology Award
06/2020, our paper “road scene labeling” reached ESI highly cited paper
11/2019, our paper “Point2Node” is accepted to AAAI 2020 as Oral Presentation
02/2019, two papers are accepted to CVPR 2019

部分论文 Selected Publications

Qiming Xia, Longhui Zheng, Shijia Zheng, Xun Huang, Hai Wu, Chenglu Wen(通讯作者), Cheng Wang, DOtA++: Unsupervised and Collaboratively Detect Objects from Multi-agent Observations with Multi-modal Prior Constraints, IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) 2026
Hai Wu, Shijia Zhao, Xun Huang, Qiming Xia, Chenglu Wen(通讯作者), Li Jiang, Xin Li, Cheng Wang, Unsupervised 3D Object Detection by Commonsense Clue, IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) 2025
Yudi Dai, Zhiyong Wang, Xiping Lin, Chenglu Wen(通讯作者), Lan Xu, Siqi Shen, Yuexin Ma, Cheng Wang, HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR, IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI) 2024
Qiming Xia, Hongwei Lin, Wei Ye, Yadan Luo, Shijia Zhao, Hai Wu, Chenglu Wen(通讯作者), Cheng Wang, Label-efficient Outdoor 3D Object Detection via Single Click Annotation from LiDAR Point Clouds, ISPRS Journal of Photogrammetry and Remote Sensing 2026
Shijia Zhao, Qiming Xia, Xusheng Guo, Pufan Zou, Maoji Zheng, Hai Wu, Chenglu Wen(通讯作者), Cheng Wang, SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts, CVPR 2025 Highlight
Qiming Xia, Wenkai Lin, Haoen Xiang, Xun Huang, Siheng Chen, Zhen Dong, Cheng Wang, Chenglu Wen(通讯作者), Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels, CVPR 2025
Xun Huang, Jinlong Wang, Qiming Xia, Siheng Chen, Bisheng Yang, Xin Li, Cheng Wang, Chenglu Wen(通讯作者), V2X-R: Cooperative LiDAR-4D Radar Fusion for 3D Object Detection with Denoising Diffusion, CVPR 2025
Hongwei Lin, Dongyu Pan, Qiming Xia, Hai Wu, Cheng Wang, Siqi Shen, Chenglu Wen(通讯作者), Pretend Benign: A Stealthy Adversarial Attack by Exploiting Vulnerabilities in Cooperative Perception, ICCV 2025
Hai Wu, Hongwei Lin, Xusheng Guo, Xin Li, Mingming Wang, Cheng Wang, Chenglu Wen(通讯作者), Motal: Unsupervised 3D Object Detection by Modality and Task-specific Knowledge Transfer, ICCV 2025
Maoji Zheng, Ziyu Xu, Qiming Xia, Hai Wu, Chenglu Wen(通讯作者), Cheng Wang, Seg2Box: 3D Object Detection by Point-Wise Semantics Supervision, AAAI 2025
Pufan Zou, Shijia Zhao, Weijie Huang, Qiming Xia, Chenglu Wen(通讯作者), Wei Li*, Cheng Wang, AdaCo: Overcoming Visual Foundation Model Noise in 3D Semantic Segmentation via Adaptive Label Correction, AAAI 2025
Xun Huang, Ziyu Xu, Hai Wu, Jinlong Wang, Chenglu Wen(通讯作者), Cheng Wang, L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection, AAAI 2025
Wei Ye, Qiming Xia, Hai Wu, Zhen Dong, Ruofei Zhong, Cheng Wang, Chenglu Wen(通讯作者), Fade3D: Fast and Deployable 3D Object Detection for Autonomous Driving, IEEE Transactions on Intelligent Transportation Systems 2025
Kezheng Xiong, Haoen Xiang, Qingshan Xu, Chenglu Wen(通讯作者), Siqi Shen, Jonathan Li, Cheng Wang, Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration, NeurIPS 2024
Hai Wu, Shijia Zhao, Xun Huang, Chenglu Wen(通讯作者), Xin Li, Cheng Wang, Commonsense Prototype for Outdoor Unsupervised 3D Object Detection, CVPR 2024
Qiming Xia, Wei Ye, Hai Wu, Shijia Zhao, Leyuan Xing, Xun Huang, Jinhao Deng, Xin Li, Chenglu Wen(通讯作者), Cheng Wang, HINTED: Hard Instance Enhanced Detector with Mixed-Density Feature Fusionfor Sparsely-Supervised 3D Object Detection, CVPR 2024
Weijie Huang, Pufan Zou, Yan Xia, Chenglu Wen(通讯作者), Yu Zang, Cheng Wang, OPOCA:One Point One Class Annotation for LiDAR Point Cloud Semantic Segmentation, IEEE Transactions on Geoscience and Remote Sensing 2024
Jinhao Deng, Wei Ye, Hai Wu, Xun Huang, Qiming Xia, Jin Fang, Wei Li*, Chenglu Wen(通讯作者), Xin Li, Cheng Wang, CMD: A Cross Mechanism Domain Adaptation Dataset for 3D Object Detection, ECCV 2024
Kezheng Xiong, Maoji Zheng, Chenglu Wen(通讯作者), Qingshan Xu, Siqi Shen*, Cheng Wang, SPEAL: Skeletal-Prior Embedded Attention Learning for Cross-Source Point Cloud Registration, AAAI 2024
Xun Huang, Hai Wu, Chenglu Wen(通讯作者), Xiaoliang Fan, Xin Li, Cheng Wang, Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection, AAAI 2024
Qiming Xia, Jinhao Deng, Chenglu Wen(通讯作者), Shaoshuai Shi, Xin Li, Cheng Wang, CoIn: Contrastive Instance Feature Mining for 3D Object Detection with Very Limited Annotations, ICCV 2024
Hai Wu, Chenglu Wen(通讯作者), Shaoshuai Shi, Xin Li, Cheng Wang, Virtual Sparse Convolution for Multimodal 3D Object Detection, CVPR 2023
Yudi Dai, YiTai Lin, XiPing Lin, Chenglu Wen(通讯作者), Lan Xu, Hongwei Yi, Siqi Shen, Yuexin Ma, Cheng Wang, SLOPER4D: A Scene-Aware Dataset For Global 4D Human Pose Estimation In Urban Environments, CVPR 2023
Qing Li, Cheng Wang, Chenglu Wen(通讯作者), Xin Li, DeepSIR: Deep Semantic Iterative Registration for LiDAR Point Clouds, Pattern Recognition(PR) 2023
Junhao Zhao, Weijie Huang, Hai Wu, Chenglu Wen(通讯作者), Bo Yang, Yulan Guo, Cheng Wang, SemanticFlow: Semantic Segmentation of Sequential LiDAR Point Clouds from Sparse Frame Annotations, IEEE Transactions on Geoscience and Remote Sensing 2023
Hai Wu, Chenglu Wen(通讯作者), Wei Li, Xin Li, Ruigang Yang, Cheng Wang, Transformation-Equivariant 3D Object Detection for Autonomous Driving, AAAI 2023
Hai Wu, Jinhao Deng, Chenglu Wen(通讯作者), Xin Li, Cheng Wang, Jonathan Li, CasA: A Cascade Attention Network for 3D Object Detection from LiDAR point clouds, IEEE Transactions on Geoscience and Remote Sensing 2022
Wenkai Han, Hai Wu, Chenglu Wen(通讯作者), et al, BLNet: Bidirectional Learning Network for Point Clouds, Computational Visual Media(CVM) 2022
Shangshu Yu, Cheng Wang, Chenglu Wen(通讯作者), Ming Cheng, Minghao Liu, Zhihong Zhang, Xin Li, LiDAR-based Localization using Universal Encoding and Memory-aware Regression, Pattern Recognition(PR) 2022
Yudi Dai, Yitai Lin, Chenglu Wen(通讯作者), Siqi Shen, Lan Xu, Jingyi Yu, Yuexi Ma, Cheng Wang, HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR, CVPR 2022
Hai Wu, Wenkai Han, Chenglu Wen(通讯作者), Xin Li, Cheng Wang, 3D Multi-Object Tracking in Point Clouds Based on Prediction Confidence-Guided Data Association, IEEE Transactions on Intelligent Transportation Systems 2021
Hai Wu, Qing Li, Chenglu Wen(通讯作者), Xin Li, Xiaoliang Fan, Cheng Wang, Tracklet Proposal Network for Multi-Object Tracking on Point Clouds, IJCAI 2021
Yudi Dai, Chenglu Wen(通讯作者), Hai Wu, Yulan Guo, Longbiao Chen, Cheng Wang, Indoor 3D Human Trajectory Reconstruction Using Surveillance Camera Videos and Point Clouds, IEEE Transactions on Circuits and Systems for Video Technology 2022
Wenkai Han, Chenglu Wen(通讯作者), Cheng Wang, Xin Li, Qing Li, Point2Node:correlation Learning of Dynamic-Node for Point Cloud Feature Modeling, AAAI 2020 oral

研究方向 Research

3D Object Detection and Tracking
The research of 3D object detection and tracking serves the perception and understanding tasks of dynamic objects on unmanned platforms. The 3D object detection and tracking methods (published in IEEE TPAMI, ICCV, CVPR, IEEE TITS, IEEE TGRS, etc.) have ranked among the top in several international autonomous driving benchmarks. VirConv-S method ranked first in the KITTI 3D car detection and BEV car detection leaderboard. The CasA++ method ranked first in the KITTI 3D Pedestrian detection. 面向高动态场景无人驾驶应用，研究高效三维运动目标检测与跟踪理论与方法，服务车辆对动态目标的感知与理解任务。研发的三维目标检测与跟踪技术（发表在IEEE TPAMI、IEEE TGRS、IEEE TITS、ICCV、CVPR 、AAAI等期刊会议上），在多个国际自动驾驶数据集榜单上名列前茅。在KITTI自动驾驶数据集上，VirConv-S方法在三维汽车检测榜单和BEV汽车检测榜单均排名第一数月，CasA++方法在三维行人检测榜单排名第一数月。

3D Scene Semantic Understanding
Oriented to the need for efficient point cloud processing, this research focuses on the deep feature description, semantic segmentation and registration of point clouds, laying a theoretical foundation for the application of complicated scene understanding. The research results were selected for the NeurIPS, AAAI Oral paper and promoted into the national and industry standards. 面向点云高效处理的需求，研究点云的深度特征描述、语义分割及配准方法，为面向多类别及变地域的场景理解应用奠定理论基础。研究成果发表在人工智能领域国际重点会议NeurIPS、AAAI 口头报告和国际期刊IEEE TGRS、PR等（ESI高被引论文1篇），推广进入国家标准计划和行业标准2项。

3D Localization and Mapping
This research aims at the localization and mapping challenges in the GNSS-denied and non-structural environment and serves the 3D perception ability of the unmanned platform. More specifically, it consists of multi-constraints-based localization and mapping under the complex platform motion, collaborative reconstruction of human motion and environment (published in IEEE TPAMI, CVPR, AAAI, etc.). This research also won the Best Paper Award at the 2017 International Mobile Mapping Conference and the 2018 featured paper of ISPRS J P&RS. 针对遮蔽空间、非结构环境下的三维定位与建图挑战，研究面向承载平台复杂运动形态下的多约束优化定位与建图、人体动作与环境协同重建等，提升无人平台对环境的三维感知能力。研究成果发表在IEEE TPAMI、CVPR等人工智能期刊和会议上。