Learning to Predict on Octree for Scalable Point Cloud Geometry Coding
Learning to Predict on Octree for Scalable Point Cloud Geometry Coding
复制标题
DOI：
10.1109/mipr54900.2022.00024
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Yixiang Mao;Yueyu Hu;Yao Wang
中科院分区：
文献类型：
--
作者：
Yixiang Mao;Yueyu Hu;Yao Wang
基于八叉树的点云表示和压缩已被MPEGG-PCC标准采用。然而，它只使用手工制作的方法来预测叶节点为非空的概率，然后将其用于熵编码。我们提出了一种用于几何编码的预测这种概率的新方法，该方法将去噪神经网络应用于既包括相邻的解码的体素又包括未编码的体素的“噪声”上下文立方体。我们进一步提出了一种基于卷积的模型，在解码器端以粗分辨率对解码的点云进行上采样。与原始的G-PCC标准和其他用于密集点云的基线方法相比，这两种方法的结合显著提高了几何编码的率失真性能。本文提出的基于八叉树的熵编码方法具有很好的可扩展性，这对于点云流媒体系统中的动态码率自适应是非常理想的。
Octree-based point cloud representation and compression have been adopted by the MPEG G-PCC standard. However, it only uses handcrafted methods to predict the probability that a leaf node is non-empty, which is then used for entropy coding. We propose a novel approach for predicting such probabilities for geometry coding, which applies a denoising neural network to a “noisy” context cube that includes both neighboring decoded voxels as well as uncoded voxels. We further propose a convolution-based model to upsample the decoded point cloud at a coarse resolution on the decoder side. Integration of the two approaches significantly improves the rate-distortion performance for geometry coding compared to the original G-PCC standard and other baseline methods for dense point clouds. The proposed octree-based entropy coding approach is naturally scalable, which is desirable for dynamic rate adaptation in point cloud streaming systems.