论文标题
多尺度云几何压缩
Multiscale Point Cloud Geometry Compression
论文作者
论文摘要
近年来，由于其现实且细粒度的3D对象和场景表示，基于点云的应用的增长。但是，以有效的交流来压缩稀疏，非结构化和高精度3D点是一个具有挑战性的问题。在本文中，利用点云的稀疏性质，我们提出了一个多尺度的端到端学习框架，该框架通过渐进的重新采样从层次上层次重建了3D点云几何（PCG）。该框架是在基于稀疏卷积的自动编码器之上开发的，用于点云压缩和重建。对于仅具有二进制占用属性的输入PCG，我们的框架将其转换为瓶颈层处的降尺度云，该层具有几何和相关的特征属性。然后，使用OCTREE编解码器无损地压缩了几何占用，并且该特征属性是使用模型的概率上下文进行了损失压缩的，该上下文与基于最先进的视频点云压缩（V-PCC）和基于几何的PCC（G-PCC）和基于几何的PCC（G-PCC）方案相比，由运动专家组（MPEG）标准比率分别降低。它的编码运行时与G-PCC相当，G-PCC仅占V-PCC的1.5％。
Recent years have witnessed the growth of point cloud based applications because of its realistic and fine-grained representation of 3D objects and scenes. However, it is a challenging problem to compress sparse, unstructured, and high-precision 3D points for efficient communication. In this paper, leveraging the sparsity nature of point cloud, we propose a multiscale end-to-end learning framework which hierarchically reconstructs the 3D Point Cloud Geometry (PCG) via progressive re-sampling. The framework is developed on top of a sparse convolution based autoencoder for point cloud compression and reconstruction. For the input PCG which has only the binary occupancy attribute, our framework translates it to a downscaled point cloud at the bottleneck layer which possesses both geometry and associated feature attributes. Then, the geometric occupancy is losslessly compressed using an octree codec and the feature attributes are lossy compressed using a learned probabilistic context model.Compared to state-of-the-art Video-based Point Cloud Compression (V-PCC) and Geometry-based PCC (G-PCC) schemes standardized by the Moving Picture Experts Group (MPEG), our method achieves more than 40% and 70% BD-Rate (Bjontegaard Delta Rate) reduction, respectively. Its encoding runtime is comparable to that of G-PCC, which is only 1.5% of V-PCC.
