潘成伟潘成伟
副教授，硕士生导师
主要研究方向
虚拟/增强现实、计算机图形学、计算机视觉、医疗图像处理等。主要从事多视频环境下的增强虚拟环境构建、基于多视图的虚拟视点合成、高逼真道路场景仿真环境构建、基于深度学习的全自动血管分割与中心线提取、医学图像中病灶分割等方向的研究。
教育经历
本科：2012年毕业于北京航空航天大学
博士：2018年毕业于北京大学计算机系，师从汪国平教授
博士后：2018年至2020年在北京大学网络所张铭教授团队进行博士后研究
个人介绍
潘成伟，北京航空航天大学副教授，近年来一直从事计算机视觉、计算机图形学方面的研究，主要研究方向为图像分析与处理、智能感知与认知、大模型安全等，尤其在人工智能算法落地应用上进行了大量探索。入选北航青年拔尖人才计划，承担国家重点研发项目子课题、科技创新2030重大项目子课题等多个项目，曾作为主要研究人员参与多项国家科学基金项目、国家重点研发计划、北京市科委重点项目等。在Science Robotics、Nature Communications、The Lancet Digital Health、Health Data Science、IEEE Transactions on Medical Imaging、AAAI、ACM MM、CIKM、MICCAI、BIBM等国际期刊、会议以及CCF A 类中文核心期刊如软件学报、计算机辅助设计与图形学学报上发表论文50余篇，曾获中国计算机辅助设计与图形学大会最佳论文奖、2022世界人工智能大会青年优秀论文提名奖、CSIAM GDC 2024最佳海报奖，申请国家发明专利10余项，授权5项。指导学生参加多项科技竞赛活动，获得了"挑战杯"全国特等奖等。
主要论文
Jingkun An, Yinghao Zhu, Zongjian Li, Enshen Zhou, Haoran Feng, Xijie Huang, Bohua Chen, Yemin Shi, Chengwei Pan. AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation[C]. AAAI 2025. CCF-A.
Xijie Huang, Xinyuan Wang, Hantao Zhang, Yinghao Zhu, Jiawen Xi, Jingkun An, Hao Wang, Hao Liang, Chengwei Pan. Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models[C]. AAAI 2025. CCF-A.
Xin Ma, Jiguang Zhang, Peng Lu1, Shibiao Xu, Chengwei Pan. Novel View Synthesis under Large-Deviation Viewpoint for Autonomous Driving[C]. AAAI 2025. CCF-A.
Bin Chen, Hongyi Li, Di Zhao, Yitang Yang, Chengwei Pan. Quality assessment of cyber threat intelligence knowledge graph based on adaptive joining of embedding model[J]. Complex & Intelligent Systems, 2025, 11(1): 1-14.
Zhiru Wang, Shiyun Xie, Chengwei Pan†, Guoping Wang. SpecGaussian with Latent Features: A High-quality Modeling of the View-dependent Appearance for 3D Gaussian Splatting[C]. ACM MM 2024: 6270-6278. CCF-A.
Ze Shi, Hongyi Li, Di Zhao, Chengwei Pan. Research on quality assessment methods for cybersecurity knowledge graphs[J]. Computers & Security, 2024, 142: 103848.
Yinghao Zhu, Zixiang Wang, Long He, Shiyun Xie, Xiaochen Zheng, Liantao Ma, Chengwei Pan. PRISM: Mitigating EHR Data Sparsity via Learning from Missing Feature Calibrated Prototype Patient Representations[C]. CIKM 2024: 3560-3569. CCF-B.
Yinghao Zhu, Changyu Ren, Zixiang Wang, Xiaochen Zheng, Shiyun Xie, Junlan Feng, Xi Zhu, Zhoujun Li, Liantao Ma, Chengwei Pan. EMERGE: Integrating RAG for Improved Multimodal EHR Predictive Modeling[C]. CIKM 2024: 3549-3559. CCF-B.
Xinyuan Wang, Chengwei Pan†, Hongming Dai, Gangming Zhao, Jinpeng Li, Xiao Zhang, Yizhou Yu. Leveraging Frequency Domain Learning in 3D Vessel Segmentation[C]. BIBM 2023: 1503-1508. CCF-B.
Gangming Zhao, Kongming Liang, Chengwei Pan*, Fandong Zhang, Xianpeng Wu, Xinyang Hu, Yizhou Yu. Graph Convolution Based Cross-Network Multi-Scale Feature Fusion for Deep Vessel Segmentation[J]. IEEE transactions on medical imaging, 2022, 42(1): 183-195. *Equal Contribution.
Chengwei Pan, Baolian Qi, Gangming Zhao, Jiaheng Liu, Chaowei Fang, Dingwen Zhang, Jinpeng Li. Deep 3D Vessel Segmentation based on Cross Transformer Network[C]. BIBM 2022: 1115-1120. CCF-B.
Chengwei Pan, Gangming Zhao, Junjie Fang, Baolian Qi, Jiaheng Liu, Chaowei Fang, Dingwen Zhang, Jinpeng Li, Yizhou Yu. Computer-aided Tuberculosis Diagnosis with Attribute Reasoning Assistance[C]. MICCAI 2022: 623-633. CCF-B.
Jiafa He, Chengwei Pan*, Can Yang, Ming Zhang, Yang Wang, Xiaowei Zhou, Yizhou Yu. Hybrid Representations for Automatic 3D Vessel Centerline Extraction[C]. MICCAI 2020: 24-34. CCF-B, Student Travel Award.
Zhao Shi, Chongchang Miao, U Joseph Schoepf, Rock H Savage, Danielle M Dargis, Chengwei Pan*, Xue Chai, Xiu Li Li, Shuang Xia, Xin Zhang, Yan Gu, Yonggang Zhang, Bin Hu, Wenda Xu, Changsheng Zhou, Song Luo, Hao Wang, Li Mao, Kongming Liang, Lili Wen, Longjiang Zhou, Yizhou Yu, Guang Ming Lu, Long Jiang Zhang. A clinically applicable deep-learning model for detecting intracranial aneurysm in computed tomography angiography images[J]. Nature communications, 2020, 11(1): 6090.
Wei Li, Chengwei Pan*, Rong Zhang, Jiaping Ren, Yuexin Ma, Jin Fang, Feilong Yan, Qichuan Geng, Xinyu Huang, Huajun Gong, Weiwei Xu, Guoping Wang, Dinesh Manocha, Ruigang Yang. AADS: Augmented Autonomous Driving Simulation using Data-driven Algorithms[J]. Science robotics, 2019, 4(28): eaaw0863.