Detail Preserved Point Cloud Completion via Separated Feature Aggregation

Abstract

Point cloud shape completion is a challenging problem in 3D vision and robotics. Existing learning-based frameworks leverage encoder-decoder architectures to recover the complete shape from a compactly encoded global feature vector. Though the global feature can approximately represent the overall latent shape, it discards some details of the original partial shape during the completion process. In this work, instead of using a global feature to recover the whole complete surface, we explore multi-level features by hierarchical feature learning and represent the existing-part and the missing-part respectively. We propose two different feature aggregation strategies, named global & local feature aggregation(GLFA) and residual feature aggregation(RFA), to express the two parts features and reconstruct coordinates from the combined features. In addition, we also design a refinement component to prevent the generated point from non-uniform distribution and outliers. Extensive experiments have been conducted on the ShapeNet and KITTI dataset. Qualitative and quantitative evaluations demonstrate that our proposed network is more capable of both preserving the original details.