A 3D Motion Vector Database for Dynamic Point Clouds

Due to the large amount of data that point clouds represent and the differences in geometry of successive frames, the generation of motion vectors for an entire point cloud dataset may require a significant amount of time and computational resources. With that in mind, we provide a 3D motion vector database for all frames of two popular dynamic point cloud datasets. The motion vectors were obtained through translational motion estimation procedure that partitions the point clouds into blocks of dimensions M x M x M , and for each block, a motion vector is estimated. Our database contains motion vectors for M = 8 and M = 16. The goal of this work is to describe this publicly available 3D motion vector database that can be used for different purposes, such as compression of dynamic point clouds.

[1]  Edson M. Hung,et al.  Local Texture and Geometry Descriptors for Fast Block-Based Motion Estimation of Dynamic Voxelized Point Clouds , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[2]  D. Graziosi,et al.  An overview of ongoing point cloud compression standardization activities: video-based (V-PCC) and geometry-based (G-PCC) , 2020, APSIPA Transactions on Signal and Information Processing.

[3]  Camilo C. Dorea,et al.  Block-Based Motion Estimation Speedup for Dynamic Voxelized Point Clouds , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).