GAMES Webinar 2019 – 124期（三维视觉前沿专题报告）|戴玉超(Northwestern Polytechnical University),高盛华 (上海科技大学)

【GAMES Webinar 2019-124期】（三维视觉前沿专题报告）

报告嘉宾1：戴玉超，Northwestern Polytechnical University

报告时间：2019年12月26日 晚上8:00-8:45（北京时间）

报告题目：Multi-view Geometry Computation: Optimization based Approaches Meet Deep Learning

报告摘要：

Computer vision is dedicated in to enabling machines/robots the visual perception ability as human. Geometric computer vision aims at reconstructing and understanding the three-dimensional geometric structure of the observed scene from images and videos, which has important applications in unmanned systems, autonomous driving, robotics, virtual reality/augmented reality and scene analysis. Deep learning, especially deep convolutional neural networks, has great advantages in feature learning and semantic information extraction. How to effectively combine this data-driven model with multi-view geometric model has become an active research area in computer vision. In this talk, I will present a series of recent work from our group in this direction, including how to achieve monocular depth estimation, binocular depth estimation and multi-view stereo under the framework of supervised learning, and how to construct unsupervised learning frameworks for the tasks of self-adaptive stereo, multi-view stereo, optical flow estimation and Stereo-Lidar fusion. The talk will finish with discussions on future research directions.

讲者简介：

Yuchao Dai is currently a Professor with School of Electronics and Information at the Northwestern Polytechnical University (NPU). He received the B.E. degree, M.E degree and Ph.D. degree all in signal and information processing from NPU, Xian, China, in 2005, 2008 and 2012, respectively. He was an ARC DECRA Fellow with the Research School of Engineering at the Australian National University, Canberra, Australia from 2014 to 2017 and a Research Fellow with the Research School of Computer Science at the Australian National University, Canberra, Australia from 2012 to 2014. His research interests include structure from motion, multi-view geometry, low-level computer vision, deep learning, compressive sensing and optimization. He won the Best Paper Award in IEEE CVPR 2012, the DSTO Best Fundamental Contribution to Image Processing Paper Prize at DICTA 2014, the Best Algorithm Prize in NRSFM Challenge at CVPR 2017, the Best Student Paper Prize at DICTA 2017 and the Best Deep/Machine Learning Paper Prize at APSIPA ASC 2017. He served as Area Chair for WACV 2019/2020, ICME 2020 and ACM MM 2019.

讲者个人主页: http://jszy.nwpu.edu.cn/daiyuchao

报告嘉宾2：高盛华，上海科技大学

报告时间：2019年12月26日 晚上8:45-9:30（北京时间）
报告题目：基于结构的三维重建

报告摘要：

图像的结构信息包括图像的线框结构、平面结构对于图像的三维场景重建有着重要的作用。相比于关键点，结构信息提供更为高阶语义新的表达，因此可以取得更为鲁棒的结果。在这个报告中，我们将介绍我们在线框提取、平面检测以及基于平面重建方面的最新研究进展。

讲者简介：

高盛华，上海科技大学研究员，副教授（终身教授)，博导，入选2015年国家青年千人计划。2012博士毕业于新加坡南洋理工大学。2014年加入上海科技大学信息学院。迄今为止，在计算机视觉领域顶级会议和期刊发表50余篇。担任CVPR ICCV等多个Workshop的主席，ICCV’2019，AAAI2019，IJCAI2020领域主席，计算机视觉领域期刊IEEE TCSVT和Neurocomputing的副主编等。他的工作入围 IJCAI2017的最佳学生论文提名。

讲者个人主页：https://svip-lab.github.io/news.html

主持人简介：

杨佳琪，西北工业大学计算机学院副教授。2014年和2019年于华中科技大学人工智能与自动化学院分别获得控制科学与工程学士和博士学位，2017年至2018年赴美国宾夕法尼亚大学GRASP实验室进行博士生联合培养，2019年7月加入西北工业大学计算机学院和空天地海一体化大数据应用国家工程实验室。研究方向包括点云局部特征提取、特征匹配、点云配准、点云语义分割、三维重建等。详情请见个人主页：http://teacher.nwpu.edu.cn/person/2019010121

GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播？”及“如何加入GAMES微信群？”的信息；
GAMES主页的“资源分享”有往届的直播讲座的视频及PPT等。
观看直播的链接：http://webinar.games-cn.org