A voxel flow-based deep unfolding reconstruction framework was proposed to perform time-dimensional super-resolution on the reconstructed video frames aiming at the problems of high reconstruction hardware burden and poor reconstruction quality of video snapshot compressed imaging (SCI) due to small compressive sampling rate. A deep denoising network was proposed based on optimized iteration to iteratively reconstruct the initial frames. The video features of the denoising network were converted into voxel flow features in order to estimate the voxel information. A motion regularizer was constructed based on voxel streams in order to compute time-dimensional super-resolved frames by using voxels from the original frames. Group convolution was combined in the model to fuse the voxel stream information at different stages to reduce the loss of motion information. The experimental results showed that the average reconstructed peak signal-to-noise ratio on the benchmark dataset was improved by 0.23 dB compared to the comparison method, and the visual quality of reconstructed frames was higher. The compressive sampling rate of the video SCI system can be significantly reduced with the same frame rate of the reconstructed video by using the proposed method in order to maintain high quality reconstruction results.