PU-CTG: A Point Cloud Upsampling Network Using Transformer Fusion and GRU Correction

Abstract

Point clouds are widely used in remote sensing applications, e.g., 3D object classification, semantic segmentation, and building reconstruction. Generating dense and uniformly distributed point clouds from low-density ones is beneficial to 3D point cloud applications. The traditional methods mainly focus on the global shape of 3D point clouds, thus ignoring detailed representations. The enhancement of detailed features is conducive to generating dense and uniform point clouds. In this paper, we propose a point cloud upsampling network to improve the detail construction ability, named PU-CTG. The proposed method is implemented by a cross-transformer-fused module and a GRU-corrected module. The aim of the cross-transformer module is to enable the interaction and effective fusion between different scales of features so that the network can capture finer features. The purpose of the gated recurrent unit (GRU) is to reconstruct fine-grained features by rectifying the feedback error. The experimental results demonstrate the effectiveness of our method. Furthermore, the ModelNet40 dataset is upsampled by PU-CTG, and the classification experiment is applied to PointNet to verify the promotion ability of this network.

3D Point Cloud Shape Generation with Collaborative Learning of Generative Adversarial Network and Auto-Encoder

“…Among these tasks, learning to generate 3D data has attracted much attention and has been studied using various methods, e.g., image-to-point cloud, image-to-mesh, point cloud-to-voxel, point cloud-to-point cloud, etc. These generated data can be used for different 3D computer vision tasks, such as reconstruction [1][2][3][4], completion [5][6][7], segmentation [8,9], object detection [10][11][12][13][14], classification [15,16] and upsampling [17][18][19][20][21]. However, there are few works tackling the task of generating 3D point clouds from noises, which can create additional training data for recognition, synthesizing new shapes, etc.…”