A typical learning-based video compression scheme consists of motion coding and residual coding. In this paper, our deep video compression features a motion predictor and a refinement networks for interframe coding. To save the bits for transmitting motion information, our scheme performs local motion prediction and sends only the differential motion vectors to the decoder. In the residual coding, we couple the residual decoder with the refine-net to reduce residual signal bits. The experiments show that our work can achieve a higher coding performance compared to the known learningbased video codecs.