In this work, we propose a high efficiency intra video coding based on data-driven transform, which is able to learn the source distributions of intra prediction residuals and improve the subsequent transform coding efficiency. Firstly, we model learning based transform design as an optimization problem of maximizing energy compaction or decorrelation. A data-driven Subspace Approximation with Adjusted Bias (Saab) transform is analyzed and compared with the mainstream Discrete Cosine Transform (DCT) on their energy compaction and decorrelation capabilities. Secondly, we propose a Saab transform based intra video coding framework with offline Saab transform learning. Meanwhile, intra mode dependent Saab transform is developed. Then, Rate-Distortion (RD) gain of Saab transform based intra video coding is theoretically and experimentally analyzed in detail. Finally, three strategies that apply the Saab transform to intra video coding are developed to improve the coding efficiency. Experimental results demonstrate that the proposed $8\times 8$ Saab transform based intra coding can achieve Bjønteggard Delta Bit Rate (BDBR) from −1.19% to −10.00% and −3.07% on average as compared with the mainstream $8\times 8$ DCT based intra coding. In case of variable size transform unit setting, the proposed algorithm achieves BDBR from −0.17% to −6.09% and −1.80% on average, which outperform the DCT based and the neural network based schemes.

中文翻译：

---

基于数据驱动变换的高效帧内视频编码

在这项工作中，我们提出了一种基于数据驱动变换的高效帧内视频编码，能够学习帧内预测残差的源分布，提高后续变换编码效率。首先，我们将基于学习的变换设计建模为最大化能量压缩或去相关的优化问题。分析了具有调整偏置 (Saab) 变换的数据驱动子空间逼近，并与主流离散余弦变换 (DCT) 的能量压缩和去相关能力进行了比较。其次，我们提出了一种基于 Saab 变换的帧内视频编码框架，该框架具有离线 Saab 变换学习。同时，开发了帧内模式相关的萨博变换。然后，对基于萨博变换的帧内视频编码的率失真（RD）增益进行了理论和实验详细分析。最后，开发了三种将 Saab 变换应用于帧内视频编码的策略，以提高编码效率。实验结果表明，所提出的 $8\乘以 8$与主流相比，基于 Saab 变换的帧内编码可以实现平均从 -1.19% 到 -10.00% 和 -3.07% 的 Bjønteggard Delta Bit Rate (BDBR) $8\乘以 8$基于 DCT 的帧内编码。在可变大小的变换单元设置的情况下，所提出的算法平均实现了从-0.17% 到-6.09% 和-1.80% 的BDBR，优于基于DCT 和基于神经网络的方案。