Perceptual Loss with Fully Convolutional for Image Residual Denoising

摘要：

　　In this paper we propose a fully convolutional encoderdecoder framework for image residual transformation tasks.Instead of only using per-pixel loss function,the proposed framework learn endto-end mapping combined with perceptual loss function that depend on low-level features from a pre-trained network.Pointing out the mapping function in order to handle noise-free image by introduce identity mapping.And through an analysis of the interplay between the neural networks and the underlying noisy distribution which they seeking to learn.We also show how to construct a uniform transform,which is then used to make a single deep neural network work well across different levels of noise.Comparing with previous approaches,ours achieves better performance.The experimental results indicate the efficiency of the proposed algorithm to cope with image denoising tasks.

关键词： Residual denoising Encoder-decoder Perceptual loss

作者: Tao Pan Fu Zhongliang Wang Lili Zhu Kai

作者单位: Chengdu Institute of Computer Application,Chinese Academy of Sciences,Chengdu 610041,China;University of Chinese Academy of Sciences,Beijing 100049,China

会议类型: 国际会议

会议名称: 第七届全国模式识别学术会议(The 7th Chinese Conference on Pattern Recognition,CCPR2016)

会议地点: 成都

会议语种:英文

页码: 122-132

在线出版日期: 2016-11-03（万方平台首次上网日期，不代表论文的发表时间）