科学研究
学术报告
当前位置: 学院主页 > 科学研究 > 学术报告 > 正文

Multi-dimensional image recovery: When tensor decomposition meets deep learning

发布时间:2021-03-29 作者: 浏览次数:
Speaker: 赵熙乐 DateTime: 2021年3月29日(周一)下午15:00-16:00
Brief Introduction to Speaker:

赵熙乐,电子科技大学教授。

Place: 腾讯会议(会议号请联系张雄军老师索取)
Abstract:Recently, tensor decomposition methods have received increasing attention for multi-dimensional image recovery. However, only considering the low-rank prior of multi-dimensional images is not sufficient for multi-dimensional image recovery, especially for extremely complex imaging scenarios. In this talk, we will discuss how to bring into play the respective strengths of tensor decomposition methods and deep learning methods for multi-dimensional image recovery. Extensive numerical examples including inpainting and denoising are delivered to demonstrate the superiority of the suggested methods over state-of-the-art methods.