个人简介
孟明，中国传媒大学数据科学与智能媒体学院讲师。2022年博士毕业于北京航空航天大学虚拟现实技术与系统国家重点实验室和虚拟现实/增强现实技术及应用国家工程实验室，导师为周忠教授与吴威教授。2022年7月中国传媒大学师资博后，2024年7月留校讲师。主要从事虚实融合、智能媒体计算（场景、数字人等）、非遗文化创意（国画、戏曲等）。
论文发表
[1]Ming Meng, Yufei Zhao, Bo Zhang, Yonggui Zhu,Weimin Shi, Maxwell Wen, Zhaoxin Fan. A Survey of Talking Head Synthesis Techniques: Portrait Generation, Driving Mechanisms, and Editing [J]. ACM Computing Surveys, 2025. (JCR Q1, IF=28.0，中科院一区TOP)
[2]Ming Meng, Ke Mu, Yonggui Zhu, Zhe Zhu, Haoyu Sun, Heyang Yan and Zhaoxin Fan. VarGes: Improving Variation in Co-Speech 3D Gesture Generation via Style-CLIPS [J]. Computational Visual Media, 2024. (JCR Q1, IF=18.3，中科院二区)
[3]Ming Meng, Xiaoping Hou, Yisheng Wang, Hanwen Liu, Yufei Zhao, Qin Yuan. PolyMotion-7K: A Multimodal-Driven Polyglot Avatar Motion Dataset [C]. The 21th International Forum of Digital Multimedia Communication, 2024.(EI检索)
[4]Ming Meng, Yi Zhou, Zhaoxin Li, Zhong Zhou. Structure Recovery from Single Omnidirectional Image with Distortion-aware Learning [J]. Journal of King Saud University - Computer and Information Sciences, 2024. (JCR Q1，IF=6.1，中科院二区)
[5]Ming Meng, Yonggui Zhu,Yufei Zhao, Zhaoxin Li, and Zhe Zhu. 3D Indoor Scene Geometry Estimation from a Single Omnidirectional Image: A Comprehensive Survey [J]. Computational Visual Media, 2024. (JCR Q1, IF=18.3，中科院二区)
[6]Ming Meng, Likai Xiao and Zhong Zhou. Geometric-driven Indoor Structure Recovery from a Single Omnidirectional Image Based on Planar Depth Maps Learning [J]. Neural Computing and Applications, 2023. (SCI期刊，IF=4.5，中科院三区)
[7]Zhong Zhou(博导), Ming Meng, Yi Zhou, Zhe Zhu, Jingdi You. Model-Guided 3D Stitching for Augmented Virtual Environment [J]. Science China Information Sciences, 2022. (JCR Q1, IF=7.6，中科院一区)
[8]Ming Meng, Likai Xiao, Yi Zhou, Zhaoxin Li, Zhong Zhou. Distortion-aware room layout estimation from a single fisheye image [C]. IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Bari, Italy, October 4-8, 2021. (CCF B 类会议)
[9]Mengfan Li, Ming Meng(通讯作者) and Zhong Zhou. RepF-Net: Distortion-aware Re-projection Fusion Network for Object Detection in Panorama Image [C]. Asian Conference on Computer Vision (ACCV), 2022. (CCF C类会议，通讯作者)
[10]Ming Meng, Yi Zhou, Chong Tan, Zhong Zhou. Viewpoint Quality Evaluation for Augmented Virtual Environment [C]. In Pacific-Rim Conference on Multimedia (PCM), Hefei, China, September 21-22, 2018. (CCF C 类会议)
[11]Fengjuan Qiao, Yonggui Zhu and Ming Meng. Efficient Image Restoration with Style-Guided Context Cluster and Interaction[J]. Neural Computing and Applications, 2024, 36: 6973-6991. (JCR Q1，IF=4.724)
[12]周颐, 孟明, 吴威, 周忠. 基于视频模型的虚拟现实视频融合系统[J]. 系统仿真学报, 2018, 30(7):2550-2557. (中文核心期刊)
[13]Mingyang Li, Yi Zhou, Ming Meng, Yuehua Wang and Zhong Zhou. 3D Room Reconstruction from a Single Fisheye Image [C]. International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, July 14-19, 2019.(CCF C 类会议)
[14]Yi Zhou, Mingjun Cao, Jingdi You, Ming Meng, Yuehua Wang and Zhong Zhou. MR Video Fusion: Interactive 3D Modeling and Stitching on Wide-baseline Videos[C]. ACM Symposium on Virtual Reality Software and Technology (VRST),Tokyo, Japan, November 28- December 01, 2018.(CCF C 类会议, 获 ACM VRST Forum8专项奖)
[15]周忠, 孟明, 周颐. 支持大规模视频融合的混合现实技术[J]. 中兴通讯技术, 2017, 23(06): 6-9.
专利授权/申请
[1] 孟明, 肖立凯, 周忠. 一种深度信息引导的全方向图像三维结构自动恢复方法[P]. 专利授权号: ZL2022115336768（专利转化）
[2] 孟明, 柴剑平, 张浩楠. 一种基于单幅RGB图像的交互双手三维重建方法及系统[P]. 专利授权号: ZL2023113711513（专利转化）
[3] 周忠, 周颐, 孟明, 庚琦川, 刘俊琦, 胡勇, 刘睿, 严柯, 吴威. 一种基于昼夜图像对进行三维立面布局估计的联合推断方法[P].专利授权号: ZL2017105595549
[4] 吴威, 周颐, 解佳琦, 孟明, 周忠. 一种虚实融合监控场景中的导览路径规划方法[P]. 专利授权号: ZL2017103517403
[5] 周颐, 孟明, 游景帝, 周忠. 一种面向实时视频融合的颜色一致性调整方法[P].专利授权号: ZL2019108352726
[6] 肖立凯，孟明，周忠，周颐. 一种室内鱼眼图像的全自动布局恢复方法[P].专利授权号: ZL202011096920X
[7] 孟明，穆柯，王妍，侯小萍，崔鸣宇，朱永贵，范肇心. 基于视觉风格特征的多样性增强协同语音动作生成系统[P].专利申请号: 202411588620.1
[8] 孟明，杨紫伊，苏镇杰，侯小萍，郝君怡，范肇心，朱永贵. 基于动态神经网络和特征调制的零样本语音克隆[P]. 专利申请号: 2024116310726