GAMES Webinar 2018-32期(ICCV 2017论文报告)| 周星壹( 德克萨斯大学奥斯汀分校),季梦奇(香港科技大学)

【GAMES Webinar 2018-32期(ICCV 2017论文报告)】
报告嘉宾1: 周星壹,德克萨斯大学奥斯汀分校
报告时间:2018年1月25日(星期四)晚20:00 – 20:45(北京时间)
主持人:贾伟,合肥工业大学(个人主页:http://ci.hfut.edu.cn/2017/0904/c3995a72289/page.htm
报告题目:Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
报告摘要:
We study the task of 3D human pose estimation in the wild. This task is challenging due to lack of training data, as existing datasets are either in the wild images with 2D pose or in the lab images with 3D pose. We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure. Our network augments a state-of-the-art 2D pose estimation sub-network with a 3D depth regression sub-network. Unlike previous two-stage approaches that train the two sub-networks sequentially and separately, our training is end-to-end and fully exploits the correlation between the 2D pose and depth estimation sub-tasks. The deep features are better learned through shared representations. In doing so, the 3D pose labels in controlled lab environments are transferred to in the wild images. In addition, we introduce a 3D geometric constraint to regularize the 3D pose prediction, which is effective in the absence of ground truth depth labels. Our method achieves competitive results on both 2D and 3D benchmarks.
讲者简介:Xingyi Zhou is a fresh Computer Science Ph.D. student at The University of Texas at Austin, working with Prof. Qixing Huang. Before coming to Austin, he graduated from School of Computer Science at Fudan University, advised by Prof. Wei Zhang and Prof. Xiangyang Xue. He has spent 6 months as a research intern at Microsoft Research Asia, working with Dr. Yichen Wei. His research focuses on computer vision and machine learning, especially for object keypoints estimation.
讲者个人主页:http://xingyizhou.xyz

 

报告嘉宾2:季梦奇,香港科技大学
报告时间:2018年1月25日(星期四)晚20:45 – 21:30(北京时间)
主持人:贾伟,合肥工业大学(个人主页:http://ci.hfut.edu.cn/2017/0904/c3995a72289/page.htm
报告题目:SurfaceNet: An End-To-End 3D Neural Network for Multiview Stereopsis
报告摘要:
经过几十年的发展,多视角立体重建仍然存在很多难点,比如在稀疏视点下视角间匹配点的选取、纹理较少区域的精确重建等,这些直接影响着模型重建的精准性和完整性。在深度学习攻城略地的当下,它又能否在多视角立体重建问题上继续发挥优势呢?经过一段时间探索我们提出了”表面重建网络”(SurfaceNet)并被ICCV2017所接收。据我们所知,这是第一个端对端的用来解决多视角三维重建问题的学习框架,也就是说图像一致性和几何结构信息都可以通过神经网络学习得到。最终的重建结果可以达到前沿水平,并且比较现有方法可以在纹理较少区域获得明显的提升。希望通过与大家交流能碰撞出更多火花。
讲者简介:
季梦奇本科硕士分别毕业于北京科技大学和香港科技大学,现博士就读于香港科技大学,目前在清华大学做访问学生(导师:方璐教授)。主要研究方向是三维立体视觉和深度学习。
讲者个人主页:https://www.researchgate.net/profile/Mengqi_Ji4

 

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

 

You may also like...