【15-23期VALSE Webinar活动】 报告嘉宾：吕健勤（香港中文大学）
主持人：张兆翔（中科院自动化所）
报告题目： Image Super-Resolution Using Deep Convolutional Networks [Slides]
报告时间：2015年7月29日晚20:00（北京时间）
文章信息：
[1] C. Dong, C. C. Loy, K. He, and X. Tang, Image Super-Resolution Using Deep Convolutional Networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015 (TPAMI).
报告摘要：We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality,
and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve tradeoffs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.
报告人简介：吕健勤，香港中文大学研究助理教授，2010年获得伦敦大学玛丽王后学院（Queen Mary University of London）博士学位，2010-2013年于Vision Semantics任博士后研究员。曾参与两项欧盟框架计划下的计算机视觉研发项目，重点研究安防与多摄像头监控系统。已发表论文40篇以上，其中包括了计算机视觉三大会议（ECCV、CVPR、ICCV）及顶级期刊 （TPAMI、IJCV）。现任IET Computer Vision 杂志副主编，并担任多个国际顶级会议和期刊的审稿人。其研究方向主要为计算机视觉、模式识别、视频处理，研究内容包括人脸分析、深度学习、视觉监控和底层图像处理等。 | 