Learned Video Compression via Joint Spatial-Temporal Correlation Exploration
This work improves video compression efficiency for applications requiring low-delay scenarios, representing an incremental advancement over existing methods.
The paper tackled video compression by exploiting temporal correlations using first-order optical flow and second-order flow prediction, achieving state-of-the-art performance with consistent gains across test sequences compared to H.265/HEVC, H.264/AVC, and another learned method.
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.