Multi-resolution Dense Network for Point Cloud Completion

Abstract

The task of 3D point cloud completion is to predict a complete point cloud from the incomplete partial point cloud. Generally, the encoder is used to extract the global shape features of the input incomplete point cloud, and then the decoder infers the complete point cloud. At present, some methods have been improved by multi-resolution encoders and multi-layer decoders, and achieved obvious results. However, these methods still cannot fully express the shape features. In order to solve this problem, we propose a feature fusion mechanism based on skip connection. The features extracted from each resolution point cloud are connected with the input of corresponding decoder. Then they are weighted and fused to obtain denser features, which can be decoded into a finer point cloud. In addition, the current loss function is still not a good measure of the similarity between two point clouds, so we also proposed a multi-stage local average Hausdroff Loss to form a joint reconstruction loss function to guide the generation of missing point clouds. Experimental results prove the effectiveness of our method in point cloud completion tasks, and show that it products better performance than existing methods.