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.
3D good continuation model explains stereo vision using neurogeometry.
New framework segments 3D scenes using neural algorithms and sub-Riemannian geometry.
Graph Neural Networks improve 3D object detection in LiDAR point clouds.
V-SysId identifies keypoints and 3D system from unlabeled videos.
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…
A machine learning method predicts rock permeability from 3D images.
STRING improves 2D and 3D position encodings for better performance.
GTA improves transformer-based NVS models by encoding geometric structure.
Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional Variational AutoEncoders which have shown great promise for learning rich representations of deformab…
Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly large volume of medical images that need to be processed. It has been demonstrated that for medical images the transmission from local to clo…
A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods…
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 …
This work generates synthetic 3D thermal facial data using 2D facial data and deep learning.
Framework for efficient defect classification and inspection.
New benchmark for non-rigid 3D human shape retrieval.
Paper extends 2D ZSAD to 3D MRI without training, achieving robust anomaly detection.
A framework for generating 3D shapes by sequentially assembling primitives.
TURB-Rot provides a large database of turbulent rotating flow snapshots for research.
Dissertation tackles zero-shot anomaly detection, focusing on consistent anomalies and proposing CoDeGraph framework.
The growing role that artificial intelligence and specifically machine learning is playing in shaping the future of wireless communications has opened up many new and intriguing research directions. This paper motivates the research in the novel direction of \textit{vision-aided wireless communications}, which aims at …
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…
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…
3D ConvNets improved with Project & Excite for medical imaging segmentation.
GCDM generates valid large 3D molecules and optimizes existing molecules.
Paper proposes Roweisposes for 3D action recognition using generalized eigenvalue problem.
Equivariant networks improve geometric prediction without scalar approximations.
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…
Enhances SSL methods with depth cues for better image understanding.
Paper predicts TUG score from gait characteristics using machine learning.
Transformer-M learns molecular data in 2D or 3D formats.
Improved 3D MRI classification using contrastive learning with continuous proxy metadata.
Centroid Transformers reduce memory and computation by summarizing inputs into centroids.
New neural network processes 3D volumes with improved equivariance.
Enhanced 3D shape analysis using information geometry.
Proposes a robust 3D classification method for sparse point clouds.
Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications. In spite of their prevalence, there are few public datasets for detailed evaluation of computer vision algorithms on fisheye images. We release the first extensive fish…
In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both …
Unified model learns concepts across domains like left and right.
Constructing of molecular structural models from Cryo-Electron Microscopy (Cryo-EM) density volumes is the critical last step of structure determination by Cryo-EM technologies. Methods have evolved from manual construction by structural biologists to perform 6D translation-rotation searching, which is extremely comput…
Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars. Tasks in autonomous robotics such as 3D object recognition, simultaneous localization and mapping (SLAM), path planning and navigation, require some form of 3D sp…
In this paper we explore the richness of information captured by the latent space of a vision-based generative model. The model combines unsupervised generative learning with a task-based performance predictor to learn and to exploit task-relevant object affordances given visual observations from a reaching task, invol…
During the past decade, with the significant progress of computational power as well as ever-rising data availability, deep learning techniques became increasingly popular due to their excellent performance on computer vision problems. The size of the Protein Data Bank has increased more than 15 fold since 1999, which …
GCPNet improves molecular graph learning for protein structure and binding.
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…
Kidney tumor segmentation emerges as a new frontier of computer vision in medical imaging. This is partly due to its challenging manual annotation and great medical impact. Within the scope of the Kidney Tumor Segmentation Challenge 2019, that is aiming at combined kidney and tumor segmentation, this work proposes a no…
Quasi-conformal (QC) theory is an important topic in complex analysis, which studies geometric patterns of deformations between shapes. Recently, computational QC geometry has been developed and has made significant contributions to medical imaging, computer graphics and computer vision. Existing computational QC theor…
Activity recognition is the ability to identify and recognize the action or goals of the agent. The agent can be any object or entity that performs action that has end goals. The agents can be a single agent performing the action or group of agents performing the actions or having some interaction. Human activity recog…
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combinatio…