? [No.17]2019-6-18Side Window Filtering-首页-山东财经大学bet365投注网址_bet365亚洲娱乐_bet365平台娱乐(官网) bet365投注网址_bet365亚洲娱乐_bet365平台娱乐

[No.17]2019-6-18Side Window Filtering

  • 2019年06月17日 09:01
  • 新IT卓越大讲堂
?新IT卓越大讲堂 No.17 期Side Window Filtering 报告题目:Side Window Filtering主讲人:Guoping Qiu时间:2019年6月18日15:30地点:燕山校区1406主办:bet365投注网址_bet365亚洲娱乐_bet365平台娱乐报告摘要:This talk will be mainly introducing our CVPR 2019 oral paper of the same title. In addition, I will briefly introduce our other recent and ongoing research including generative adversarial network (GAN) ba...

新IT卓越大讲堂 No.17 期

Side Window Filtering

报告题目:Side Window Filtering

主讲人:Guoping Qiu

时间:2019年6月18日15:30

地点:燕山校区1406

主办:bet365投注网址_bet365亚洲娱乐_bet365平台娱乐

报告摘要:

This talk will be mainly introducing our CVPR 2019 oral paper of the same title. In addition, I will briefly introduce our other recent and ongoing research including generative adversarial network (GAN) based image dehazing, deep learning based image companding, inverse halftoning, down scaling, decolorization and HDR tone mapping, amongst others. Local windows are routinely used in computer vision and almost without exception the center of the window is aligned with the pixels being processed. We show that this conventional wisdom is not universally applicable. When a pixel is on an edge, placing the center of the window on the pixel is one of the fundamental reasons that cause many filtering algorithms to blur the edges. Based on this insight, we propose a new Side Window Filtering (SWF) technique which aligns the window's side or corner with the pixel being processed. The SWF technique is surprisingly simple yet theoretically rooted and very effective in practice. We show that many traditional linear and nonlinear filters can be easily implemented under the SWF framework. Extensive analysis and experiments show that implementing the SWF principle can significantly improve their edge preserving capabilities and achieve state of the art performances in applications such as image smoothing, denoising, enhancement, structure-preserving texture-removing, mutual-structure extraction, and HDR tone mapping. In addition to image filtering, we further show that the SWF principle can be extended to other applications involving the use of a local window. Using colorization by optimization as an example, we demonstrate that implementing the SWF principle can effectively prevent artifacts such as color leakage associated with the conventional implementation. Given the ubiquity of window based operations in computer vision, the new SWF technique is likely to benefit many more applications. .

报告人简介:

Guoping Qiu is a Professor of Visual Information Processing at the University of Nottingham, Nottingham, UK, and a Distinguished Professor of Information Engineering, Director of Intelligent Robotics Centre at Shenzhen University, China. He has taught in universities in the UK and Hong Kong and also consulted for multinational companies in Europe, Hong Kong and China. His research interests include image processing, pattern recognition, and machine learning. He is particularly known for his pioneering research in high dynamic range imaging and machine learning based image processing technologies. He has published widely and holds several European and US patents. Technologies developed in his lab have laid the cornerstone for successful spinout companies who are developing advanced digital photography software enjoyed by tens of millions of global users.

相关推荐