Related papers: Density-encoded line integral convolution: polaris…
For the analysis of systems consisting of small, regular objects, the methods of mathematical morphology applied to images of these systems are well-suited. One of these methods is the use of Voronoi polygons. It was found that the Voronoi…
One of the main goals of modern observational cosmology is to map the large scale structure of the Universe. A potentially powerful approach for doing this would be to exploit three-dimensional spectral maps, i.e. the specific intensity of…
In this paper, we propose a novel medical image segmentation using iterative deep learning framework. We have combined an iterative learning approach and an encoder-decoder network to improve segmentation results, which enables to precisely…
This work introduces a new unsupervised representation learning technique called Deep Convolutional Transform Learning (DCTL). By stacking convolutional transforms, our approach is able to learn a set of independent kernels at different…
The effective receptive field (ERF) plays an important role in transform coding, which determines how much redundancy can be removed during transform and how many spatial priors can be utilized to synthesize textures during inverse…
We introduce a unified approach that, given a strong gravitationally lensed polarised source, self-consistently infers its complex surface brightness distribution and the lens galaxy mass-density profile, magnetic field and electron density…
Deconvolutional layers have been widely used in a variety of deep models for up-sampling, including encoder-decoder networks for semantic segmentation and deep generative models for unsupervised learning. One of the key limitations of…
Delineation of curvilinear structures is an important problem in Computer Vision with multiple practical applications. With the advent of Deep Learning, many current approaches on automatic delineation have focused on finding more powerful…
Constrained image splicing detection and localization (CISDL) is a newly proposed challenging task for image forensics, which investigates two input suspected images and identifies whether one image has suspected regions pasted from the…
Learned image compression (LIC) has shown great promise for achieving high rate-distortion performance. However, current LIC methods are often limited in their capability to model the complex correlation structures inherent in natural…
Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…
This work proposes a new approach to study transport properties of highly correlated local structures. The method, dubbed the Logarithmic Discretization Embedded Cluster Approximation (LDECA), consists of diagonalizing a finite cluster…
We propose the structure and color based learned image codec (SLIC) in which the task of compression is split into that of luminance and chrominance. The deep learning model is built with a novel multi-scale architecture for Y and UV…
Monocular depth estimation is a fundamental yet challenging task in computer vision, especially under complex conditions such as textureless surfaces, transparency, and specular reflections. Recent diffusion-based approaches have…
One of the essential tasks in medical image analysis is segmentation and accurate detection of borders. Lesion segmentation in skin images is an essential step in the computerized detection of skin cancer. However, many of the…
Recently learned image compression (LIC) has achieved great progress and even outperformed the traditional approach using DCT or discrete wavelet transform (DWT). However, LIC mainly reduces spatial redundancy in the autoencoder networks…
We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a…
Polar codes were introduced in 2009 by Arikan as the first efficient encoding and decoding scheme that is capacity achieving for symmetric binary-input memoryless channels. Recently, this code family was extended by replacing the…
This study demonstrates the feasibility of a novel fabrication technique for high spatial resolution CsI: Tl scintillation detectors tailored for single photon emission computed tomography (SPECT) systems. Building upon our previously…
We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a…