论文标题
改进的深点云几何压缩
Improved Deep Point Cloud Geometry Compression
论文作者
论文摘要
点云已被认为是3D含量的关键数据结构，在许多应用中至关重要的是虚拟和混合现实，自主驾驶，文化遗产等。在本文中，我们提出了一组贡献，以改善深点云压缩，即使用用于入围拷贝编码的量表超高模型；采用更深入的变换；局部损失的平衡重量不同；用于解码的最佳阈值；和顺序模型训练。此外，我们还提供了有关这些因素中每个因素的影响的广泛消融研究，以便更好地了解它们为何改善RD性能。当使用点对点（点对上的）度量时，提出的改进的最佳组合分别比G-PCC Trisoup和OCTREE的BD-PSNR分别获得了5.50（6.48）dB和6.84（5.95）dB的OCTREE。代码可在https://github.com/mauriceqch/pcc_geo_cnn_v2上找到。
Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc. In this paper, we propose a set of contributions to improve deep point cloud compression, i.e.: using a scale hyperprior model for entropy coding; employing deeper transforms; a different balancing weight in the focal loss; optimal thresholding for decoding; and sequential model training. In addition, we present an extensive ablation study on the impact of each of these factors, in order to provide a better understanding about why they improve RD performance. An optimal combination of the proposed improvements achieves BD-PSNR gains over G-PCC trisoup and octree of 5.50 (6.48) dB and 6.84 (5.95) dB, respectively, when using the point-to-point (point-to-plane) metric. Code is available at https://github.com/mauriceqch/pcc_geo_cnn_v2 .
