As a crucial part of video compression, intra prediction utilizes local information of images to eliminate the redundancy in spatial domain. In both the High Efficiency Video Coding (H.265/HEVC) and Versatile Video Coding (H.266/VVC), multiple directional prediction modes are employed to find the texture trend of each small block and then the prediction is made based on reference samples in the selected direction. Recently, the intra prediction schemes based on neural networks have achieved great success. In these methods, the networks are trained and applied to intra prediction to assist the directional prediction modes. In this paper, we propose a novel tree-structured data clustering-driven neural network (dubbed TreeNet) for intra prediction, which builds the networks and clusters the training data in a tree-structured manner. Specifically, in each network split and training process of TreeNet, every parent network on a leaf node is split into two child networks by adding or subtracting Gaussian random noise. Then a data clustering-driven training is applied to train the two derived child networks using the clustered training data of their parent. To test the performance, TreeNet is integrated into VVC and HEVC to combine with or replace the directional prediction modes. In addition, a fast termination strategy is proposed to accelerate the search of TreeNet. The experimental results demonstrate that TreeNet with the fast termination can reach an average of 2.8% Bjontegaard distortion rate (BD-rate) improvement (up to 8.1%) and 4.9% BD-rate improvement (up to 8.2%) over VVC (VTM-4.0) and HEVC (HM-16.9) with all intra configuration, respectively.
翻译:作为视频压缩的一个关键部分,内部预测利用当地图像信息消除空间域域的冗余。在高效率视频编码(H.265/HEVC)和Versatile视频编码(H.266/VVC)中,使用了多种方向预测模式,以寻找每个小块的纹理趋势,然后根据选定方向的参考样本作出预测。最近,基于神经网络的内部预测计划取得了巨大成功。在这些方法中,这些网络经过培训,用于内部预测,以协助方向预测模式。在本文件中,我们提议为内部预测建立一个新型的树结构数据组合驱动的神经网络(dubbed TreaNet),以树结构化的方式构建网络,以构建每个小块块块的网络纹理趋势,然后根据选定方向的参考样本样本进行预测。最近,基于神经网络网络网络网络网络的每个母网络通过增减高尔西亚随机噪音而分裂成两个儿童网络。然后,用数据组合组合式改进软件来培训两个衍生的儿童网络,使用其父的分组培训数据,用于搜索系统驱动的神经网络驱动的神经网络驱动神经网络(dustretrod Tell-ralalalalal-ral-ral-ralalalalal-deal-hal-deal-hal-al-deal-deal-al-deal-de)分别测试一个测试,以快速B-rvial-rvial-rvial-ral-ral-rvial-rvial-ral-ral-ral-ral-ral-ral-ral-late-late-late-late-de-tod-lation-de-de-toxxxxxxxxxxxxxxxx-tox-to-to-to-toxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-x-x-xxxxxx-x-x-x-x-x-x-x-toxxxxxxxxxxxxxxxxxxxxxx-x-x-xxx-