arXiv research

DreamFusion uses text-to-image diffusion models to create 3D images efficiently.

Understanding the three-dimensional (3D) structure of the genome is essential for elucidating vital biological processes and their links to human disease. To determine how the genome folds within the nucleus, chromosome conformation capture methods such as HiC have recently been employed. However, computational methods…

3D convolutional neural networks are difficult to train because they are parameter-expensive and data-hungry. To solve these problems we propose a simple technique for learning 3D convolutional kernels efficiently requiring less training data. We achieve this by factorizing the 3D kernel along the temporal dimension, r…

3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. However, interpreting the decision making process of these 3D-CNNs is still an infeasible task. In this paper, we present a unique 3D-CNN based Gradient-weighted Class Activation Mapping method (3D…

Noise2Filter improves 3D tomography reconstruction efficiency and accuracy.

Transformer-M learns molecular data in 2D or 3D formats.

Deep learning models predict option prices from 3D tensor data.

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 …

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…

This work generates synthetic 3D thermal facial data using 2D facial data and deep learning.

A novel deep learning architecture (XmasNet) based on convolutional neural networks was developed for the classification of prostate cancer lesions, using the 3D multiparametric MRI data provided by the PROSTATEx challenge. End-to-end training was performed for XmasNet, with data augmentation done through 3D rotation a…

GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.

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…

Improved 3D LiDAR data classification using product coefficients.

3D RadViz improves 3D data visualization of multidimensional datasets.

3D convolutional neural networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. In this paper, we present a 3D-CNN based method to learn distinct local geometric features of interest within an object. In this context, the voxelized representation may not be sufficient to captu…

Graph Neural Networks improve 3D object detection in LiDAR point clouds.

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…

New benchmark for non-rigid 3D human shape retrieval.

3D object detection improved using energy-based models.

3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and o…

When using Convolutional Neural Networks (CNNs) for segmentation of organs and lesions in medical images, the conventional approach is to work with inputs and outputs either as single slice (2D) or whole volumes (3D). One common alternative, in this study denoted as pseudo-3D, is to use a stack of adjacent slices as in…

DISPR uses diffusion models to predict 3D cell shapes from 2D images.

GCDM generates valid large 3D molecules and optimizes existing molecules.

Graph Neural Networks model 3D granular flow simulations.

Training 3D object detectors for autonomous driving has been limited to small datasets due to the effort required to generate annotations. Reducing both task complexity and the amount of task switching done by annotators is key to reducing the effort and time required to generate 3D bounding box annotations. This paper…

GAGA accelerates 3D molecular generation by replacing long trajectories with Gaussian approximations.

SE(3)-Transformers maintain equivariance for 3D data under rotations and translations.

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 …

Improved 3D MRI classification using contrastive learning with continuous proxy metadata.

New method reconstructs 3D shapes from 2D images using Kendall's shape space.

One of the challenges of using machine learning techniques with medical data is the frequent dearth of source image data on which to train. A representative example is automated lung cancer diagnosis, where nodule images need to be classified as suspicious or benign. In this work we propose an automatic synthetic lung …

This paper proposes the adaptation of Support Vector Data Description (SVDD) to the multiple kernel case (MK-SVDD), based on SimpleMKL. It also introduces a variant called Slim-MK-SVDD that is able to produce a tighter frontier around the data. For the sake of comparison, the equivalent methods are also developed for O…

We study knots in 3d Chern-Simons theory with complex gauge group $SL(N,\mathbb{C})$, in the context of its relation with 3d $\mathcal{N}=2$ theory (the so-called 3d-3d correspondence). The defect has either co-dimension 2 or co-dimension 4 inside the 6d $(2,0)$ theory, which is compactified on a 3-manifold $\hat{M}$. …

3D models vulnerable to adversarial attacks, new method improves success rate and naturalness.

Study 3d N=1 vacua from M-theory compactification on Spin(7) space.

3D filament plots visualize curves in datasets, avoiding visual clutter.

The paper proposes methods for volumetric parameterization of 3D solid manifolds.

Study of 3d-3d correspondence involving $q$-Weyl algebra and 3d-index.

The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms, high-performance 3D manycore platforms that incorporate both CPUs and GPUs present a pr…

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…

Tab2vox converts tabular data into 3D images for improved demand forecasting.

Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation pipeline requires numerous design decisions such as the selection of 3D shapes and …

Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional latent scenes, due to challenges in both modeling and inference. Accounting for th…

SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.

Deep neural network models used for medical image segmentation are large because they are trained with high-resolution three-dimensional (3D) images. Graphics processing units (GPUs) are widely used to accelerate the trainings. However, the memory on a GPU is not large enough to train the models. A popular approach to …

Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. However, applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of structured data. Here, we propose LatticeNet, a novel approach for 3D sema…

DALES offers a large annotated aerial LiDAR dataset for 3D deep learning.