The point cloud we obtained from LiDAR or depth camera may usually have some kind of missing part due to the obstacles and the insufficient of resolution. Finding a way to complete these missing parts comes to be essential for the understanding of point cloud. The previous methods tend to have a strict limitation on the input size or output size of point cloud, which leads to some kind of sparsification of the points and can not actually be applied to various scenarios. In this paper, we provide a self-adaptive method where both the input size and output size can be flexible and don’t have any hard limitations on them. We apply the AABB box to convert the problem into 2D image plane and take use of hierarchically depth image painting to complete the task. The experiment shows that our method has a self-adaptive ability to give various output without strict limitations while maintaining the local detail of the point cloud.