A GMM-based method generates new 3D structures from medical images.
problem Generating new medical images from limited data and different modalities.
method Gaussian Mixture Model (GMM) for point-cloud generation.
result Generated point-clouds closely match training samples from the same class.
The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving. One commonly used 3D data type is 3D point clouds, which describe shape information. We examine the problem of creating robust models from the …
A novel method compares 3D point clouds using information geometry.
problem Comparing 3D point clouds in machine learning applications.
method Interprets point clouds as probability density functions on a statistical manifold, using GMM and Modified Symmetric KL divergence.
result Demonstrates effectiveness through various case studies.
LatticeNet segments 3D point clouds faster and more efficiently.
problem Challenges in applying CNNs to 3D point cloud data.
method Embeds point cloud geometry into a permutohedral lattice for fast convolutions.
result Achieves state-of-the-art performance in 3D segmentation.
Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve inter-class discrimination efficiently. In this paper, we propose a two-faceted sol…
Deep learning within the context of point clouds has gained much research interest in recent years mostly due to the promising results that have been achieved on a number of challenging benchmarks, such as 3D shape recognition and scene semantic segmentation. In many realistic settings however, snapshots of the environ…
The paper introduces REQNNs for robust 3D point cloud processing.
problem 3D point cloud processing robustness to rotations.
method Revised neural networks using quaternion features for rotation-equivariance.
result REQNNs exhibit higher rotation robustness compared to original networks.
This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models. The main idea of the method is to treat a point cloud as a probability density in 3D space that is modeled using a cloud-specific neural network. To capture the similarity between point clouds we rely o…
SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.
problem Lack of resources and transparency in 3D semantic segmentation models.
method SCENE-Net uses signature shapes identified via GENEOs to achieve semantic segmentation with minimal resources.
result SCENE-Net achieves comparable IoU to state-of-the-art methods with less data and computational resources.
Graph Neural Networks improve 3D object detection in LiDAR point clouds.
problem Challenges in processing LiDAR data due to its 3D geometry and massive volume.
method Proposes a Graph Neural Network (GNN) based framework for 3D object detection.
result GNNs successfully identify objects in 3D LiDAR point clouds.
3D object classification and segmentation using deep neural networks has been extremely successful. As the problem of identifying 3D objects has many safety-critical applications, the neural networks have to be robust against adversarial changes to the input data set. There is a growing body of research on generating h…
3D capsule network for point clouds handles rotations and translations.
problem Processing 3D point clouds with equivariance and invariance.
method Quaternion equivariant capsule network with dynamic routing on quaternions.
result Parsimonious capsule network disentangles geometry and pose.
Mapper-GIN simplifies 3D point cloud classification with lightweight structure.
problem Robust 3D point cloud classification under corruption.
method Mapper algorithm for structural decomposition, GIN for graph classification.
result Mapper-GIN achieves competitive accuracy with minimal parameters.
Proposes a robust 3D classification method for sparse point clouds.
problem Invariance to rotation, positional shift, scaling, and robustness to point sparsity in point cloud classification.
method Introduces a graph-based feature learning approach with an end-to-end neural network.
result Significantly improves 3D object classification and retrieval tasks with sparse point clouds.
A new rotation invariant method for 3D medical imaging classification.
problem Computational expense and lack of rotation invariance in 3D medical image processing.
method Proposes a rotation invariant convolution operator using hypersphere topology.
result Demonstrates improved classification accuracy and rotation invariance.
Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challenging tasks including 3D points generation, reconstruction, compression…
Proposes QMC-based QSW for 3D SW distance.
problem Intractable SW distance in 3D.
method Quasi-Monte Carlo (QMC) for QSW approximations.
result QMC-based QSW improves SW estimation.
Graph convolutional neural networks (Graph-CNNs) extend traditional CNNs to handle data that is supported on a graph. Major challenges when working with data on graphs are that the support set (the vertices of the graph) do not typically have a natural ordering, and in general, the topology of the graph is not regular …
A new method for generating realistic and creative 3D shapes from point clouds.
problem Generating realistic and creative 3D shapes from point clouds.
method Learning to interpolate point clouds by encoding prior knowledge about real-world objects.
result Generated 3D shapes are both realistic and creative, unlike any existing forms.
PointGMM learns hGMMs from point clouds for 3D shape representation.
problem Lack of shape priors and non-local information in point cloud representations.
method Neural network that learns hierarchical Gaussian mixture models (hGMMs) for 3D shapes.
result Generative model learns meaningful latent space for interpolations and novel shape synthesis.
Paper reduces false positives in lung nodule detection using deep learning on point clouds.
problem Reduces false positives in lung nodule detection.
method Uses deep learning models for point clouds to transform 3D CT scan data.
result Achieved 85.98 FROC compared to 77.26 FROC for baseline models.
Advanced 3D metrology technologies such as Coordinate Measuring Machine (CMM) and laser 3D scanners have facilitated the collection of massive point cloud data, beneficial for process monitoring, control and optimization. However, due to their high dimensionality and structure complexity, modeling and analysis of point…
The paper analyzes different neural network architectures for 3D point cloud processing.
problem Understanding the effects of specific intermediate-layer network architectures on 3D point cloud processing.
method Designing five metrics to diagnose various types of DNNs and conducting comparative studies.
result The hypotheses on the effects of specific intermediate-layer network architectures on the representation capacity of DNNs are verified.
Enhanced 3D shape analysis using information geometry.
problem Challenges in comparing 3D point clouds due to their unstructured nature and complex geometry.
method Information geometric framework for 3D point cloud shape analysis using Gaussian Mixture Models (GMMs) on a statistical manifold. Proposed MSKL divergence with upper and lower bounds.
result MSKL provides stable and monotonically varying values that directly reflect geometric variation, outperforming traditional distances and existing KL approximations.
Develops a method for conformal parameterization of point clouds without fixed boundaries.
problem Desirable distortion in fixed-boundary parameterizations of point clouds.
method Free-boundary conformal parameterization method involving approximation of point cloud Laplacian and boundary treatment.
result High-quality point cloud meshing achieved through the proposed method.
SE(3)-Transformers maintain equivariance for 3D data under rotations and translations.
problem Ensuring stable and predictable performance in 3D data under transformations.
method Introducing a self-attention module that is equivariant under continuous 3D roto-translations.
result The SE(3)-Transformer outperforms non-equivariant and non-attention models on real-world datasets.
When classifying point clouds, a large amount of time is devoted to the process of engineering a reliable set of features which are then passed to a classifier of choice. Generally, such features - usually derived from the 3D-covariance matrix - are computed using the surrounding neighborhood of points. While these fea…
pyLOT library simplifies machine learning on 3D point clouds via linearized optimal transport.
problem Performing machine learning tasks on 3D point clouds.
method Linearized optimal transport (LOT) to embed distributions into Hilbert space, enabling linear machine learning.
result Downstream tasks on embedded representations are simplified to linear operations.
Bayesian neural networks improve uncertainty estimation in 3D point cloud segmentation for factory planning.
problem Improving uncertainty estimation in 3D point cloud segmentation for factory planning.
method Proposed fully Bayesian and approximate Bayesian neural networks for point cloud segmentation.
result Superior model performance and improved segmentation results with uncertainty incorporation.
In recent decades, the use of 3D point clouds has been widespread in computer industry. The development of techniques in analyzing point clouds is increasingly important. In particular, mapping of point clouds has been a challenging problem. In this paper, we develop a discrete analogue of the Teichmüller extremal mapp…
Geometric Capsule Autoencoders group 3D points into parts and objects.
problem Learning object representations from 3D point clouds.
method Geometric capsules with pose and feature components, Multi-View Agreement voting mechanism.
result Learned representations enable object identification and canonical pose recovery.
Paper improves deep point cloud compression techniques.
problem Efficiently compressing 3D point cloud data for various applications.
method Integrates scale hyperprior model, deeper transforms, focal loss, and optimal thresholding.
result Achieves significant BD-PSNR gains over existing methods.
The concept of a Point Cloud has played an increasingly important role in many areas of Engineering, Science, and Mathematics. Examples are: LIDAR, 3D-Printing, Data Analysis, Computer Graphics, Machine Learning, Mathematical Visualization, Numerical Analysis, and Monte Carlo Methods. Entering point cloud into Google r…
LION generates high-quality 3D shapes using hierarchical latent diffusion models.
problem Creating high-quality 3D shapes for digital artists.
method Hierarchical Latent Point Diffusion Model (LION) with a global shape latent and point-structured latent space.
result LION achieves state-of-the-art generation performance on ShapeNet benchmarks.
We explore the intersection of human and machine creativity by generating sculptural objects through machine learning. This research raises questions about both the technical details of automatic art generation and the interaction between AI and people, as both artists and the audience of art. We introduce two algorith…
PointTriNet generates 3D triangulations from point clouds efficiently and scalably.
problem Generating a triangulation among a set of points in 3D space.
method Iteratively applies a classification network and a proposal network over nearby points and triangles, using a novel triangle-relative input encoding.
result Generates robust and scalable triangulations for 3D learning pipelines.
This paper introduces a new Urban Point Cloud Dataset for Automatic Segmentation and Classification acquired by Mobile Laser Scanning (MLS). We describe how the dataset is obtained from acquisition to post-processing and labeling. This dataset can be used to learn classification algorithm, however, given that a great a…
DALES offers a large annotated aerial LiDAR dataset for 3D deep learning.
problem Lack of large-scale annotated aerial LiDAR datasets for deep learning.
method Collection and annotation of over half a billion hand-labeled points from an ALS scanner.
result DALES is the most extensive publicly available ALS data set with improved resolution and coverage.
Object detection in point cloud data is one of the key components in computer vision systems, especially for autonomous driving applications. In this work, we present Voxel-FPN, a novel one-stage 3D object detector that utilizes raw data from LIDAR sensors only. The core framework consists of an encoder network and a c…
A novel method compresses point cloud attributes by folding them onto a 2D grid.
problem Efficiently compressing point cloud attributes for storage and transmission.
method Interpreting point clouds as 2D manifolds, folding onto a grid, and mapping attributes to the grid using optimized methods.
result The proposed folding-based approach achieves performance comparable to state-of-the-art codecs.
Bayesian segmentation and uncertainty estimation improve 3D model accuracy for factory planning.
problem Generating accurate 3D models from outdated and incomplete 2D data.
method Bayesian neural network for point cloud segmentation and entropy-based uncertainty estimation.
result Bayesian segmentation network significantly improves model accuracy and object identification.
Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised learning tasks such as object classification and semantic segmentation. While mas…
Deep 3D models are vulnerable to isometry transformations under adversarial attacks.
problem Vulnerability of deep 3D models to isometry transformations under adversarial attacks.
method Developed a black-box attack with success rate over 95% and a novel white-box attack framework.
result Deep 3D models are extremely vulnerable to isometry transformations under adversarial attacks.
This research detects and identifies human-made objects in 3D point clouds using novel methods.
problem Detect and identify human-made objects in 3D point clouds.
method Ground filtering, local information extraction, clustering using Marked Point Fields (MPFs) and Hessian matrix.
result The proposed method outperforms previous techniques in detecting human-made objects.
New method uses scalar-based models to approximate spherical tensors efficiently.
problem Efficiently approximating spherical tensors with equivariant functions.
method Expressing equivariant functions as the product of a scalar function and a small tensor basis.
result Approximations are fast, simple to implement, and accurate in practical settings.
Point cloud is the most fundamental representation of 3D geometric objects. Analyzing and processing point cloud surfaces is important in computer graphics and computer vision. However, most of the existing algorithms for surface analysis require connectivity information. Therefore, it is desirable to develop a mesh st…
Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots. Certain existing studies have split input point clouds into small regions such as 1m x 1m; one reason for this is that models in the studies cannot consume a large number of poi…
Torch-Points3D simplifies 3D deep learning research and reproducibility.
problem Lack of transparency and reproducibility in 3D deep learning research.
method Modular framework with quality-of-life features, standardized protocols, and open-source implementation.
result Facilitates fair and rigorous evaluation of 3D deep learning methods.