arXiv research

3D Axial-Attention improves lung nodule classification accuracy.

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

GTA improves transformer-based NVS models by encoding geometric structure.

Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.

We describe a deep learning approach for automated brain hemorrhage detection from computed tomography (CT) scans. Our model emulates the procedure followed by radiologists to analyse a 3D CT scan in real-world. Similar to radiologists, the model sifts through 2D cross-sectional slices while paying close attention to p…

Centroid Transformers reduce memory and computation by summarizing inputs into centroids.

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

For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory cues from numerous trials, e.g., by looking at and touching objects. Despite its importance, multisensory 3D scene representation learning has received less attention compared to t…

Paper extends 2D ZSAD to 3D MRI without training, achieving robust anomaly detection.

A framework for generating 3D shapes by sequentially assembling primitives.

We propose a method to generate multiple diverse and valid human pose hypotheses in 3D all consistent with the 2D detection of joints in a monocular RGB image. We use a novel generative model uniform (unbiased) in the space of anatomically plausible 3D poses. Our model is compositional (produces a pose by combining par…

NeRF-VAE generates 3D scenes with geometric structure from few images.

Study smoothings of singular intersections of ellipsoids.

Accurate prediction of drug-target interaction (DTI) is essential for in silico drug design. For the purpose, we propose a novel approach for predicting DTI using a GNN that directly incorporates the 3D structure of a protein-ligand complex. We also apply a distance-aware graph attention algorithm with gate augmentatio…

Paper proposes Sinkformers for Transformers with doubly stochastic attention.

The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and the design of accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition…

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set, models used to address them should be permutation invariant. We present an attenti…

We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels. The goal is to learn an implicit representation of the environment at a higher, more abstract level. We propose to use a generative approach based on Generative Query N…

Understanding the 3-dimensional structure of the world is a core challenge in computer vision and robotics. Neural rendering approaches learn an implicit 3D model by predicting what a camera would see from an arbitrary viewpoint. We extend existing neural rendering to more complex, higher dimensional scenes than previo…

Deep learning is attracting significant interest in the neuroimaging community as a means to diagnose psychiatric and neurological disorders from structural magnetic resonance images. However, there is a tendency amongst researchers to adopt architectures optimized for traditional computer vision tasks, rather than des…

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…

In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial observability, their level of importance are often different. In this paper, we propose a dee…

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability…

RADAR uses diffusion models to detect anomalies without reconstruction, improving accuracy and efficiency.

In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of complicated policies. Since the views may frequently suffer from partial observabilit…

Structure based ligand discovery is one of the most successful approaches for augmenting the drug discovery process. Currently, there is a notable shift towards machine learning (ML) methodologies to aid such procedures. Deep learning has recently gained considerable attention as it allows the model to "learn" to extra…

Predicting RNA base distances using a large language model.

Driver drowsiness increases crash risk, leading to substantial road trauma each year. Drowsiness detection methods have received considerable attention, but few studies have investigated the implementation of a detection approach on a mobile phone. Phone applications reduce the need for specialised hardware and hence, …

BCAE-2D compresses 3D data from a time projection chamber at high speed.

We briefly review the current situation with various relations between knot/braid polynomials (Chern-Simons correlation functions), ordinary and extended, considered as functions of the representation and of the knot topology. These include linear skein relations, quadratic Plucker relations, as well as "differential" …

The paper constructs and classifies 3D Walker manifolds with specific structures.

The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other regularities across scenes, such decompositions can simplify reasoning and facilitate imagination of novel scenarios. In particu…

Capsule Networks have great potential to tackle problems in structural biology because of their attention to hierarchical relationships. This paper describes the implementation and application of a Capsule Network architecture to the classification of RAS protein family structures on GPU-based computational resources. …

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 $\hat{M}$. …

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

This paper embeds surfaces in 3D spheres and balls with minimal area.

Experimental determination of protein function is resource-consuming. As an alternative, computational prediction of protein function has received attention. In this context, protein structural classification (PSC) can help, by allowing for determining structural classes of currently unclassified proteins based on thei…

3D dual field theories for Virasoro minimal models constructed using Seifert fiber spaces.

3D flying wings created for any angle asymptotic cones.

This work designs an active world model learning system with progress-based curiosity.

Proposes a new effective central charge for 3d N=2 theories.

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…

Smooth 3D flows from non-smooth starting points.

3D steady gradient Ricci solitons are all O(2)-symmetric.

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

Automated detection of MS lesions improves to 67% with 7T MRI.

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…

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…