报告嘉宾:施柏鑫(北京大学) 万人杰(南洋理工大学) 报告时间:2018年04月11日(星期三)晚上20:00(北京时间) 报告题目:A concurrent deep learning model to remove reflections 主持人:朱鹏飞(天津大学) 报告人简介: 施柏鑫,分别于2007年、2010年、2013年从北京邮电大学、北京大学、日本东京大学获得工学学士、工学硕士、博士(信息科学与技术)学位。2017年5月入选中组部“千人计划”青年项目,同年11月加入北京大学信息科学技术学院数字媒体所任研究员、博士生导师,“相机智能”课题组负责人。入职北大之前,2013至2016年曾先后在麻省理工学院媒体实验室、新加坡科技设计大学、新加坡南洋理工大学从事博士后研究,2016至2017年曾在日本国立产业技术综合研究所人工智能研究中心任研究员。曾获2015年国际计算摄像学大会(ICCP)第二最佳论文,发表于2015年国际计算机视觉大会(ICCV)的论文作为当年最优秀论文之一(1700选9)被邀请投稿至计算机视觉国际期刊(IJCV)。担任亚洲计算机视觉大会ACCV18、国际机器视觉应用会议MVA17领域主席。 个人主页:http://www.shiboxin.com 报告人简介: Renjie Wan is currently a fourth-year PhD student from Nanyang Technological University in Singapore, under the supervision of Prof. Alex C. Kot and Prof. Boxin Shi. Prior to that, he received his Bachelor degree from the University of Electronic Science and Technology of China in 2012. His research interest is the computational photography. 相关文献: 1. Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Wen Gao, and Alex C. Kot, Region-Aware Reflection Removal with Unified Content and Gradient Priors, TIP 2018 (To appear) 2. Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C. Kot, CRRN: Multi-Scale Guided Concurrent Reflection Removal Network, CVPR 2018 3. Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C. Kot, Benchmarking single-image reflection removal algorithms, ICCV 2017 4. Renjie Wan, Boxin Shi, Ah-Hwee Tan, and Alex C. Kot, Depth of field guided reflection removal, ICIP 2016 报告摘要: Removing the undesired reflections from images taken through the glass is of broad application to various computer vision tasks. Many different methods have been proposed to address the limitations existed in this problems. In this talk, we comprehensively study the properties of the reflections existed in the real world with an emphasis on the data-driven learning based methods. Specifically, we propose a concurrent reflection removal model to tackle this problem in a unified manner. To evaluate the performance of our proposed method, we also collect a large-scale evaluation dataset and our approaches have shown its effectiveness in real-world dataset and different applications. 特别鸣谢本次Webinar主要组织者: VOOC责任委员:朱鹏飞(天津大学) VODB协调理事:章国锋(浙江大学) |
小黑屋|手机版|Archiver|Vision And Learning SEminar
GMT+8, 2024-11-22 00:09 , Processed in 0.015290 second(s), 15 queries .
Powered by Discuz! X3.4
Copyright © 2001-2020, Tencent Cloud.