Content Adaptive and Error Propagation Aware Deep Video Compression
This work addresses video compression inefficiencies for applications requiring high-quality streaming or storage, though it is incremental as it builds on existing learning-based methods.
The paper tackles error propagation and lack of content adaptability in learning-based video compression by proposing a system that uses joint training across multiple frames and an online encoder updating scheme, achieving state-of-the-art performance on benchmark datasets without increasing model size or reducing decoding speed.
Recently, learning based video compression methods attract increasing attention. However, the previous works suffer from error propagation due to the accumulation of reconstructed error in inter predictive coding. Meanwhile, the previous learning based video codecs are also not adaptive to different video contents. To address these two problems, we propose a content adaptive and error propagation aware video compression system. Specifically, our method employs a joint training strategy by considering the compression performance of multiple consecutive frames instead of a single frame. Based on the learned long-term temporal information, our approach effectively alleviates error propagation in reconstructed frames. More importantly, instead of using the hand-crafted coding modes in the traditional compression systems, we design an online encoder updating scheme in our system. The proposed approach updates the parameters for encoder according to the rate-distortion criterion but keeps the decoder unchanged in the inference stage. Therefore, the encoder is adaptive to different video contents and achieves better compression performance by reducing the domain gap between the training and testing datasets. Our method is simple yet effective and outperforms the state-of-the-art learning based video codecs on benchmark datasets without increasing the model size or decreasing the decoding speed.