The first step in the construction of a regression model or a data-driven analysis, aiming to
predict or elucidate the relationship between the atomic-scale structure of matter and its …

Point cloud data have been widely explored due to its superior accuracy and robustness
under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved …

As 3D point clouds become the representation of choice for multiple vision and graphics
applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds …

Abstract Three-dimensional (3D) object recognition is widely used in automated driving,
medical image analysis, virtual/augmented reality, artificial intelligence robots, and other …

Recent deep networks that directly handle points in a point set, eg, PointNet, have been
state-of-the-art for supervised learning tasks on point clouds such as classification and …

Abstract 3D shape recognition has attracted much attention recently. Its recent advances
advocate the usage of deep features and achieve the state-of-the-art performance. However …

Three-dimensional geometric data offer an excellent domain for studying representation
learning and generative modeling. In this paper, we look at geometric data represented as …

Multi-view projection methods have demonstrated their ability to reach state-of-the-art
performance on 3D shape recognition. Those methods learn different ways to aggregate …

Despite their great success, there is still no comprehensive theoretical understanding of
learning with Deep Neural Networks (DNNs) or their inner organization. Previous work …

Point cloud is an important type of geometric data structure. Due to its irregular format, most
researchers transform such data to regular 3D voxel grids or collections of images. This …