Our paper, titled as "Learned Video Compression via Joint Spatial-Temporal Correlation Exploration", has been accepted by the AAAI-20 that will be held at the New York City in Feb 2020.
Congrats to Haojie, Tong and Ming. And, really appreciate the support from the Horizon Robotics during the summer 2019. Our gratitudes are directed to Han Shen, Lichao Huang, and many others for their warmhearted help.
Abstract:
Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Efficient temporal information representation plays a key role in video coding. Thus, in this paper, we propose to exploit the temporal correlation using both first-order optical flow and second-order flow prediction. We suggest an one-stage learning approach to encapsulate flow as quantized features from consecutive frames which is then entropy coded with adaptive contexts conditioned on joint spatial-temporal priors to exploit second-order correlations. Joint priors are embedded in autoregressive spatial neighbors, co-located hyper elements and temporal neighbors using ConvLSTM recurrently. We evaluate our approach for the low-delay scenario with High-Efficiency Video Coding (H.265/HEVC), H.264/AVC and another learned video compression method, following the common test settings. Our work offers the state-of-the-art performance, with consistent gains across all popular test sequences.