GRNet takes 3D grids as intermediate representations to complete point clouds. In the Voxel-based methods, 3D-EPN maps voxelized 3D shapes into a probabilistic latent space and completes single objects by 3D convolution operations. Experiments are conducted on widely used benchmarks and several TLS data, which demonstrate that our method outperforms other state-of-the-art methods by a 4.72% reduction of the average Chamfer Distance of categories in PCN dataset at least, and can generate finer shapes of point clouds on partial TLS data.īenefiting from the emergence of large-scale point cloud datasets and the improvement of computer technology, researchers have tried many approaches to tackle the issue of point cloud completion by the way of deep learning, which can be divided into three categories: Voxel-based methods, MLP-based (Multilayer Perception) methods and Attention-based methods. Moreover, we propose two essential blocks cross-attention perception (CAP) and self-attention augment (SAA), which replace KNN operations with attention mechanisms and are able to establish long-range geometric relationships among points by selecting neighborhoods adaptively at the global level.
The network follows a novel siamese auto-encoder architecture, to learn prior geometric information of complete shapes by aligning keypoints of complete-partial pairs during the stage of training.
In this paper, we propose a keypoints-aligned siamese (KASiam) network for the completion of partial TLS point clouds. However, existing methods mainly followed an ordinary auto-encoder architecture with only partial point clouds as inputs, and adopted K-Nearest Neighbors (KNN) operations to extract local geometric features, which takes insufficient advantage of input point clouds and has limited ability to extract features from long-range geometric relationships, respectively. Completing point clouds from partial terrestrial laser scannings (TLS) is a fundamental step for many 3D visual applications, such as remote sensing, digital city and autonomous driving.
0 kommentar(er)
