Memory-Efficient Network for Large-scale Video Compressive Sensing
This work addresses a practical bottleneck in large-scale video SCI applications by reducing memory requirements, enabling broader deployment in real-world scenarios.
The paper tackles the problem of high memory usage in deep learning methods for video snapshot compressive imaging (SCI) by developing a memory-efficient network based on multi-group reversible 3D convolutional neural networks, achieving state-of-the-art performance with less memory on both simulation and real data.
Video snapshot compressive imaging (SCI) captures a sequence of video frames in a single shot using a 2D detector. The underlying principle is that during one exposure time, different masks are imposed on the high-speed scene to form a compressed measurement. With the knowledge of masks, optimization algorithms or deep learning methods are employed to reconstruct the desired high-speed video frames from this snapshot measurement. Unfortunately, though these methods can achieve decent results, the long running time of optimization algorithms or huge training memory occupation of deep networks still preclude them in practical applications. In this paper, we develop a memory-efficient network for large-scale video SCI based on multi-group reversible 3D convolutional neural networks. In addition to the basic model for the grayscale SCI system, we take one step further to combine demosaicing and SCI reconstruction to directly recover color video from Bayer measurements. Extensive results on both simulation and real data captured by SCI cameras demonstrate that our proposed model outperforms previous state-of-the-art with less memory and thus can be used in large-scale problems. The code is at https://github.com/BoChenGroup/RevSCI-net.