Related papers: Deep DIC: Deep Learning-Based Digital Image Correl…

We propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i.e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs). The…

In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional…

This study investigated the potential of end-to-end deep learning tools as a more effective substitute for FEM in predicting stress-strain fields within 2D cross sections of arterial wall. We first proposed a U-Net based fully convolutional…

Deep neural networks face several challenges in hyperspectral image classification, including high-dimensional data, sparse distribution of ground objects, and spectral redundancy, which often lead to classification overfitting and limited…

Accurate segmentation of retinal vessels is a basic step in Diabetic retinopathy(DR) detection. Most methods based on deep convolutional neural network (DCNN) have small receptive fields, and hence they are unable to capture global context…

We consider the problem of 3D seismic inversion from pre-stack data using a very small number of seismic sources. The proposed solution is based on a combination of compressed-sensing and machine learning frameworks, known as…

Accurate measuring the location and orientation of individual particles in a beam monitoring system is of particular interest to researchers in multiple disciplines. Among feasible methods, gaseous drift chambers with hybrid pixel sensors…

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…

Deep visual recognition models are usually trained and evaluated using metrics such as loss and accuracy. While these measures show whether a model is improving, they reveal very little about how its internal representations change during…

Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome…

Image registration is used in many medical image analysis applications, such as tracking the motion of tissue in cardiac images, where cardiac kinematics can be an indicator of tissue health. Registration is a challenging problem for deep…

In medical image segmentation, particularly in UNet-like architectures, upsampling is primarily used to transform smaller feature maps into larger ones, enabling feature fusion between encoder and decoder features and supporting multi-scale…

Current continuous sign language recognition (CSLR) methods struggle with handling diverse samples. Although dynamic convolutions are ideal for this task, they mainly focus on spatial modeling and fail to capture the temporal dynamics and…

Classical monocular vSLAM/VO methods suffer from the scale ambiguity problem. Hybrid approaches solve this problem by adding deep learning methods, for example by using depth maps which are predicted by a CNN. We suggest that it is better…

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in…

LiDAR-based place recognition is an essential and challenging task both in loop closure detection and global relocalization. We propose Deep Scan Context (DSC), a general and discriminative global descriptor that captures the relationship…

Articulated object pose estimation is a core task in embodied AI. Existing methods typically regress poses in a continuous space, but often struggle with 1) navigating a large, complex search space and 2) failing to incorporate intrinsic…

It is difficult to precisely annotate object instances and their semantics in 3D space, and as such, synthetic data are extensively used for these tasks, e.g., category-level 6D object pose and size estimation. However, the easy annotations…

Dynamic Mode Decomposition (DMD) is a numerical method that seeks to fit timeseries data to a linear dynamical system. In doing so, DMD decomposes dynamic data into spatially coherent modes that evolve in time according to exponential…

Predicting the behaviour of complex systems is one of the main goals of science. An important example is plastic deformation of micron-scale crystals, a process mediated by collective dynamics of dislocations, manifested as broadly…