个人简介
季梦奇，博士，北京航空航天大学人工智能研究院副教授。2019年至2021年于清华大学成像与智能技术实验室从事博士后研究。本科与硕博分别毕业于北京科技大学和香港科技大学，期间曾访问德国慕尼黑工大、波恩大学、马普所等研究机构。围绕光场计算重建领域的前沿基础问题开展多年研究，针对大基线角及非均匀动态散射等对光场重建带来的难题，提出了多维光场隐式编码技术、物理表面跨模态融合感知等原创方法，突破了对稠密观测与强标注的双重依赖，领域专家IEEE/ACM Fellow Ravi Ramamoorthi、马尔奖得主Luc Van Gool等文章认为实现了鲁棒、完整的光场重建。相关成果发表在2篇《Nature》子刊（Nature Machine Intelligence和Light: Science & Applications）、计算机视觉顶刊IEEE TPAMI、顶会ICCV等，单篇最高引用194。
曾主持国家自然科学基金面上项目、中国博士后科学基金特别资助和面上等项目，曾入选中国博士后国际交流计划（引进项目）、清华高精尖中心未来芯片学者计划、香港科技大学海外研究奖励计划等。
Experience
2021.12-Current: Associate Professor at Beihang University (BUAA)
2019.11-2021.11: Posdoc at Tsinghua University. Supervisors: Prof. Qionghai Dai and Prof. Lu Fang
2018.04-2018.09: Visited Prof. Andreas Geiger at MPI (Intelligent System), Tuebingen, Germany
2016.09-2017.05: Visited Prof. Juergen Gall at Uni-bonn, Bonn, Germany
2014.07-2015.06: Visited Prof. Eckehard Steinbach at TUM, Munich, Germany
2012.08-2019.08: M.Sc. and Ph.D. at HKUST, Hong Kong. PhD Thesis: Learning to Perceive 3D Surface, supervised by Prof. Ling Shi and Prof. Lu Fang
2008.08-2012.06: B.Eng. at USTB, Beijing
近期论文
查看导师新发文章
（温馨提示：请注意重名现象，建议点开原文通过作者单位确认）
Surface Material Perception Through Multimodal LearningShi Mao#, Mengqi Ji#, Bin Wang, IEEE Journal of Selected Topics in Signal Processing (JSTSP 2022)
Engram-Driven VideographyLu Fang, Mengqi Ji, Xiaoyun Yuan, Jing He, Jianing Zhang, Yinheng Zhu, Haitian Zheng, Leyao Liu, Bin Wang, Qionghai Dai*Engineering 2022
SurRF: Unsupervised Multi-view Stereopsis by Learning Surface Radiance FieldJinzhi Zhang#, Mengqi Ji#, Guangyu Wang, Zhiwei Xue, Shengjin Wang, *IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2021)
A Modular Hierarchical Array Camera#, Mengqi Ji#, Jiamin Wu, David Brady, Qionghai Dai, Lu Fang*Light: Science & Applications (LSA 2020, Nature Press, Cover Paper)
Boosting Single Image Super-Resolution Learnt From Implicit Multi-Image PriorDingjian Jin, Mengqi Ji, Lan Xu, Gaochang Wu, Liejun Wang, *IEEE Transactions on Image Processing (TIP 2021)
GigaMVS: A Benchmark for Ultra-large-scale Gigapixel-level 3D ReconstructionJianing Zhang#, Jinzhi Zhang#, Shi Mao#, Mengqi Ji, Guangyu Wang, Zequn Chen, Tian Zhang, Xiaoyun Yuan, , *IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2021)
SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-view StereopsisMengqi Ji#, Jinzhi Zhang#, Qionghai Dai, Lu Fang*IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2020)
Augmenting Vascular Disease Diagnosis by Vasculature-aware Unsupervised LearningYong Wang#, Mengqi Ji#, Shengwei Jiang#, Xukang Wang, Jiamin Wu, Feng Duan, Jingtao Fan, Laiqiang Huang, Shaohua Ma*, Lu Fang*, Qionghai Dai*Nature Machine Intelligence (NMI 2020, Nature Press)
Zoom in to the Details of Human-centric VideosGuanghan Li, Yaping Zhao, Mengqi Ji, Xiaoyun Yuan, *IEEE International Conference on Image Processing (ICIP 2020)
A Learning-Based Model to Evaluate Hospitalization Priority in COVID-19 PandemicsYichao Zheng#, Yinheng Zhu#, Mengqi Ji, Rongpin Wang, Xinfeng Liu, Mudan Zhang, Jun Liu, Xiaochun Zhang, Choo Hui Qin, *, *Patterns (Cell Press)
SPI-Optimizer: An Integral-Separated PI Controller for Stochastic OptimizationDan Wang#, Mengqi Ji#, Yong Wang, Haoqian Wang, *IEEE International Conference on Image Processing (ICIP 2019)
Crossnet: An End-to-end Reference-based Super Resolution Network Using Cross-scale Warping, Mengqi Ji,, Haoqian Wang, , *Proceedings of the European conference on computer vision (ECCV 2018)
Regnet: Learning the Optimization of Direct Image-to-image Pose RegistrationLei Han, Mengqi Ji, , Matthias Nie nerarXiv:1812.10212
SurfaceNet: An End-To-End 3D Neural Network for Multiview StereopsisMengqi Ji, , , , *IEEE Conference on Computer Vision and Pattern Recognition (ICCV 2017)
Learning Cross-scale Correspondence and Patch-based Synthesis for Reference-based Super-Resolution., Mengqi Ji, Lei Han, Ziwei Xu, Haoqian Wang, , *Proceedings of the IEEE International Conference on Computer Vision.
Deep Learning for Surface Material Classification Using Haptic and Visual Information, , Mengqi Ji, Matti Strese; Yigitcan zer; Eckehard SteinbachIEEE Transactions on Multimedia (TMM 2016)
京公网安备 11010802027423号