Point cloud is a data representation of a three-dimensional object or scene. It is created by collecting a large number of spatial coordinate points, which are used to discretely represent the surface information of a three-dimensional object. Compared to traditional two-dimensional images, point clouds are particularly suited to the presentation of three-dimensional models and geospatial information. They have had a significant impact on the development of smart cities, autonomous driving applications, and augmented reality technology. However, due to the irregularity, disorganisation, diversity and other shortcomings of the point cloud, the traditional point cloud compression faces significant challenges. This paper will review the traditional coding methods and focus on the current cutting-edge artificial intelligence technology to bring the point cloud compression advances. It will also consider the future development direction.