IEEE Trans Image Process. 2018 Jul;27(7):3236-3247. doi: 10.1109/TIP.2018.2817044.
This paper proposes a deep learning method for intra prediction. Different from traditional methods utilizing some fixed rules, we propose using a fully connected network to learn an end-to-end mapping from neighboring reconstructed pixels to the current block. In the proposed method, the network is fed by multiple reference lines. Compared with traditional single line-based methods, more contextual information of the current block is utilized. For this reason, the proposed network has the potential to generate better prediction. In addition, the proposed network has good generalization ability on different bitrate settings. The model trained from a specified bitrate setting also works well on other bitrate settings. Experimental results demonstrate the effectiveness of the proposed method. When compared with high efficiency video coding reference software HM-16.9, our network can achieve an average of 3.4% bitrate saving. In particular, the average result of 4K sequences is 4.5% bitrate saving, where the maximum one is 7.4%.
本文提出了一种用于帧内预测的深度学习方法。与传统方法利用一些固定规则不同，我们提出使用全连接网络来学习从相邻重建像素到当前块的端到端映射。在所提出的方法中，网络由多条参考线提供信息。与传统的基于单一线的方法相比，更多地利用了当前块的上下文信息。因此，所提出的网络有可能生成更好的预测。此外，所提出的网络在不同的比特率设置下具有良好的泛化能力。在特定比特率设置下训练的模型在其他比特率设置下也能很好地工作。实验结果证明了所提出方法的有效性。与高效视频编码参考软件 HM-16.9 相比，我们的网络可以平均节省 3.4%的比特率。特别是，4K 序列的平均结果为节省 4.5%的比特率，其中最大的为节省 7.4%。
