Deep Learning for Video Compressive Sensing

We investigate deep learning for video compressive sensing within the scope of snapshot compressive imaging (SCI). In video SCI, multiple high-speed frames are modulated by different coding patterns and then a low-speed detector captures the integration of these modulated frames. In this manner, each captured measurement frame incorporates the information of all the coded frames in which the reconstruction algorithms are employed to recover the high speed video afterwards. In this paper, we employ both an end-to-end convolution neural network (E2E-CNN) and a plug-andplay (PnP) framework with deep denoising priors to solve the inverse problem. Considering the speed, accuracy and flexibility, different solutions are recommended for different applications.