SoftPool++: An Encoder-Decoder Network for Point Cloud Completion

Abstract

We propose a novel convolutional operator for the task of point cloud completion. One striking characteristic of our approach is that, conversely to related work it does not require any max-pooling or voxelization operation. Instead, the proposed operator used to learn the point cloud embedding in the encoder extracts permutation-invariant features from the point cloud via a soft-pooling of feature activations, which are able to preserve fine-grained geometric details. These features are then passed on to a decoder architecture. Due to the compression in the encoder, a typical limitation of this type of architectures is that they tend to lose parts of the input shape structure. We propose to overcome this limitation by using skip connections specifically devised for point clouds, where links between corresponding layers in the encoder and the decoder are established. As part of these connections, we introduce a transformation matrix that projects the features from the encoder to the decoder and vice-versa. The quantitative and qualitative results on the task of object completion from partial scans on the ShapeNet dataset show that incorporating our approach achieves state-of-the-art performance in shape completion both at low and high resolutions.

arXiv commentAccepted in International Journal of Computer Vision

References in corpus (9)

• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• ShapeNet: An Information-Rich 3D Model Repository
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
• Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
• Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
• Dense 3D Object Reconstruction from a Single Depth View
• Point Set Voting for Partial Point Cloud Analysis