Deep Fully-Connected Networks for Video Compressive Sensing
This work addresses video reconstruction for compressive sensing applications, but it appears incremental as it builds on existing architectures with deeper networks.
The authors tackled video compressive sensing by proposing a deep learning framework that recovers video frames in seconds with significantly improved reconstruction quality compared to previous methods, as demonstrated through extensive simulations.
In this work we present a deep learning framework for video compressive sensing. The proposed formulation enables recovery of video frames in a few seconds at significantly improved reconstruction quality compared to previous approaches. Our investigation starts by learning a linear mapping between video sequences and corresponding measured frames which turns out to provide promising results. We then extend the linear formulation to deep fully-connected networks and explore the performance gains using deeper architectures. Our analysis is always driven by the applicability of the proposed framework on existing compressive video architectures. Extensive simulations on several video sequences document the superiority of our approach both quantitatively and qualitatively. Finally, our analysis offers insights into understanding how dataset sizes and number of layers affect reconstruction performance while raising a few points for future investigation. Code is available at Github: https://github.com/miliadis/DeepVideoCS