Deep Guided Attention Network for Joint Denoising and Demosaicing in Real Image

扫码查看

原文链接

万方数据

外文摘要：Denoising(DN)and demosaicing(DM)are the first crucial stages in the image signal processing pipeline.Recently,researches pay more attention to solve DN and DM in a joint manner,which is an extremely un-determined inverse problem.Existing deep learning methods learn the desired prior on synthetic dataset,which lim-its the generalization of learned network to the real world data.Moreover,existing methods mainly focus on the raw data property of high green information sampling rate for DM,but occasionally exploit the high intensity and signal-to-noise(SNR)of green channel.In this work,a deep guided attention network(DGAN)is presented for real image joint DN and DM(JDD),which considers both high SNR and high sampling rate of green information for DN and DM,respectively.To ease the training and fully exploit the data property of green channel,we first train DN and DM sub-networks sequentially and then learn them jointly,which can alleviate the error accumulation.Besides,in order to support the real image JDD,we collect paired raw clean RGB and noisy mosaic images to conduct a realis-tic dataset.The experimental results on real JDD dataset show the presented approach performs better than the state-of-the-art methods,in terms of both quantitative metrics and qualitative visualization.

外文关键词：

Image denoisingImage demosaicingJoint processingGuided attentionPaired real dataset

作者：

Tao ZHANG、Ying FU、Jun ZHANG

展开 >

作者单位：

School of Computer Science and Technology,Beijing Institute of Technology,Beijing 100081,China

Advanced Reasearch Institute of Multidisciplinary Science,Beijing Institute of Technology,Beijing 100081,China

基金：

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaNational Natural Science Foundation of China

项目编号：

621710386182790162088101

出版年：

2024

DOI：

10.23919/cje.2022.00.414

电子学报(英文)

CSTPCDEI

ISSN：1022-4653

年,卷(期)：2024.33(1)

参考文献量47