Related papers: Symmetria: A Synthetic Dataset for Learning in Poi…

In order to retain more feature information of local areas on a point cloud, local grouping and subsampling are the necessary data structuring steps in most hierarchical deep learning models. Due to the disorder nature of the points in a…

Despite the notable accomplishments of deep object detection models, a major challenge that persists is the requirement for extensive amounts of training data. The process of procuring such real-world data is a laborious undertaking, which…

The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. from laser…

Symmetry, a central concept in understanding the laws of nature, has been used for centuries in physics, mathematics, and chemistry, to help make mathematical models tractable. Yet, despite its power, symmetry has not been used extensively…

Recently, 3D point cloud classification has made significant progress with the help of many datasets. However, these datasets do not reflect the incomplete nature of real-world point clouds caused by occlusion, which limits the practical…

The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many…

Recent years have witnessed the surge of learned representations that directly build upon point clouds. Though becoming increasingly expressive, most existing representations still struggle to generate ordered point sets. Inspired by…

In this paper, we propose a simple yet effective method to represent point clouds as sets of samples drawn from a cloud-specific probability distribution. This interpretation matches intrinsic characteristics of point clouds: the number of…

Machine learning heavily relies on data, but real-world applications often encounter various data-related issues. These include data of poor quality, insufficient data points leading to under-fitting of machine learning models, and…

Processing point cloud data is an important component of many real-world systems. As such, a wide variety of point-based approaches have been proposed, reporting steady benchmark improvements over time. We study the key ingredients of this…

Diffusion models have recently been employed to generate high-quality images, reducing the need for manual data collection and improving model generalization in tasks such as object detection, instance segmentation, and image perception.…

In this paper, we introduce a novel method for comparing 3D point clouds, a critical task in various machine learning applications. By interpreting point clouds as samples from underlying probability density functions, the statistical…

Latent representations learned by neural networks often exhibit semantic structure, where concept similarity is reflected by geometric proximity in embedding space. However, comparing such spaces across models remains difficult: changes in…

Persistent Homology is a widely used topological data analysis tool that creates a concise description of the topological properties of a point cloud based on a specified filtration. Most filtrations used for persistent homology depend…

Point cloud completion aims to reconstruct complete 3D shapes from partial observations, which is a challenging problem due to severe occlusions and missing geometry. Despite recent advances in multimodal techniques that leverage…

Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI, deep learning has been successfully used…

Unsupervised point cloud completion aims at estimating the corresponding complete point cloud of a partial point cloud in an unpaired manner. It is a crucial but challenging problem since there is no paired partial-complete supervision that…

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to…

Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying symmetry is present only in an idealized…

We introduce a novel framework for Continual Learning in 3D object classification. Our approach, CL3D, is based on the selection of prototypes from each class using spectral clustering. For non-Euclidean data such as point clouds, spectral…