4.7 Article

Adaptive Deep PnP Algorithm for Video Snapshot Compressive Imaging

期刊

INTERNATIONAL JOURNAL OF COMPUTER VISION
卷 131, 期 7, 页码 1662-1679

出版社

SPRINGER
DOI: 10.1007/s11263-023-01777-y

关键词

Snapshot compressive imaging; Deep learning; Deep plug-and-play; Neural networks; Computational imaging

向作者/读者索取更多资源

In this paper, an online deep optimization algorithm is proposed for video snapshot compressive imaging, which has better adaptability and performance. Furthermore, a deep demosaicing prior is introduced to address the challenge of color video imaging.
Video Snapshot compressive imaging (SCI) is a promising technique to capture high-speed videos, which transforms the imaging speed from the detector to mask modulating and only needs a single measurement to capture multiple frames. The algorithm to reconstruct high-speed frames from the measurement plays a vital role in SCI. In this paper, we consider the promising reconstruction algorithm framework, namely plug-and-play (PnP), which is flexible to the encoding process comparing with other deep learning networks. One drawback of existing PnP algorithms is that they use a pre-trained denoising network as a plugged prior while the training data of the network might be different from the task in real applications. Towards this end, in this work, we propose the online PnP algorithm which can adaptively update the network's parameters within the PnP iteration; this makes the denoising network more applicable to the desired data in the SCI reconstruction. Furthermore, for color video imaging, RGB frames need to be recovered from Bayer pattern or named demosaicing in the camera pipeline. To address this challenge, we design a two-stage reconstruction framework to optimize these two coupled ill-posed problems and introduce a deep demosaicing prior specifically for video demosaicing in SCI. Extensive results on both simulation and real datasets verify the superiority of our adaptive deep PnP algorithm.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据