A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The paper introduces REQNNs for robust 3D point cloud processing.
Graph Neural Networks improve 3D object detection in LiDAR point clouds.
Generative neural network designs novel 3D molecules with specified properties.
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…
Proposes a method to improve skull stripping accuracy in MRI images.
We propose a predictive neural network architecture that can be utilized to update reference velocity models as inputs to the full waveform inversion. Deep learning models are explored to augment velocity model building workflows during processing the 3D seismic volume in salt-prone environments. Specifically, a neural…
Graph Neural Networks model 3D granular flow simulations.
A neural scene representation framework enforcing 3D transformations.
Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…
We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer's disease classification. One approach conducts sensitivity analysis on hierarchical 3D image segmentation, and the other two visualize network activations on a spatial map. Visual chec…
Enhances safety of 3D object detection neural networks.
Pattern recognition methods using neuroimaging data for the diagnosis of Alzheimer's disease have been the subject of extensive research in recent years. In this paper, we use deep learning methods, and in particular sparse autoencoders and 3D convolutional neural networks, to build an algorithm that can predict the di…
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 …
Generative model for 3D point clouds using invertible flows.
Large prospective epidemiological studies acquire cardiovascular magnetic resonance (CMR) images for pre-symptomatic populations and follow these over time. To support this approach, fully automatic large-scale 3D analysis is essential. In this work, we propose a novel deep neural network using both CMR images and pati…
In neural networks, it is often desirable to work with various representations of the same space. For example, 3D rotations can be represented with quaternions or Euler angles. In this paper, we advance a definition of a continuous representation, which can be helpful for training deep neural networks. We relate this t…
Lung cancer is the leading cause of cancer-related death worldwide. Early diagnosis of pulmonary nodules in Computed Tomography (CT) chest scans provides an opportunity for designing effective treatment and making financial and care plans. In this paper, we consider the problem of diagnostic classification between beni…
Differentiable voxelization for 3D meshes with GPU acceleration.
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
Deep-learning method estimates bone 3D structure from X-ray images.
A scalable deep learning framework accelerates training of large neural networks for solving 3D Poisson equations.
3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful r…
New neural network processes 3D volumes with improved equivariance.
The paper analyzes different neural network architectures for 3D point cloud processing.
Study evaluates using multiple slices as input for CNNs in medical image segmentation.
This paper analyzes the use of 3D Convolutional Neural Networks for brain tumor segmentation in MR images. We address the problem using three different architectures that combine fine and coarse features to obtain the final segmentation. We compare three different networks that use multi-resolution features in terms of…
Bayesian neural networks improve uncertainty estimation in 3D point cloud segmentation for factory planning.
Transformer-M learns molecular data in 2D or 3D formats.
A new 2.5D U-net for 3D segmentation reduces memory constraints.
Geometric GNNs model 3D atomic systems with rotations and translations.
Proposes a neural network for recognizing 3D skeleton-based interactions.
Physics-constrained neural nets solve EM fields of charged particle beams.
BPI models 2D patterns on multiple planes and 3D scene from a single image.
DMGNN predicts 3D human motions using adaptive multiscale graphs.
EuLearn creates diverse 3D topological datasets for machine learning.
Decussation improves robustness of 3D neural networks.
This paper explores the capabilities of convolutional neural networks to deal with a task that is easily manageable for humans: perceiving 3D pose of a human body from varying angles. However, in our approach, we are restricted to using a monocular vision system. For this purpose, we apply a convolutional neural networ…
PointTriNet generates 3D triangulations from point clouds efficiently and scalably.
The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape represe…
Early diagnosis, playing an important role in preventing progress and treating the Alzheimer\{'}s disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocamp…
We solve 6-DoF localisation and 3D reconstruction using deep state-space models.
New benchmarks for RNA 3D structure-function modeling.
Generative Multisensory Network learns 3D scene representations from multiple modalities.
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…
Early diagnosis, playing an important role in preventing progress and treating the Alzheimer's disease (AD), is based on classification of features extracted from brain images. The features have to accurately capture main AD-related variations of anatomical brain structures, such as, e.g., ventricles size, hippocampus …
BGNNs model particle-boundary interactions efficiently.
Topology-enhanced loss improves 3D object reconstruction from 2D images.
Neural Processes combine the strengths of neural networks and Gaussian processes to achieve both flexible learning and fast prediction in stochastic processes. However, a large class of problems comprises underlying temporal dependency structures in a sequence of stochastic processes that Neural Processes (NP) do not e…