Related papers: Residual-Recursion Autoencoder for Shape Illustrat…

Time series with missing data are signals encountered in important settings for machine learning. Some of the most successful prior approaches for modeling such time series are based on recurrent neural networks that transform the input and…

The utilization of biometric authentication with pattern images is increasingly popular in compact Internet of Things (IoT) devices. However, the reliability of such systems can be compromised by image quality issues, particularly in the…

An important component of autoencoders is the method by which the information capacity of the latent representation is minimized or limited. In this work, the rank of the covariance matrix of the codes is implicitly minimized by relying on…

In this work we test the ability of deep learning methods to provide an end-to-end mapping between low and high resolution images applying it to the iris recognition problem. Here, we propose the use of two deep learning single-image…

We present a novel approach for super-resolution that utilizes implicit neural representation (INR) to effectively reconstruct and enhance low-resolution videos and images. By leveraging the capacity of neural networks to implicitly encode…

Deep learning-based super-resolution methods have shown great promise, especially for single image super-resolution (SISR) tasks. Despite the performance gain, these methods are limited due to their reliance on copious data for model…

Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias…

Recently, convolutional auto-encoders (CAE) were introduced for image coding. They achieved performance improvements over the state-of-the-art JPEG2000 method. However, these performances were obtained using massive CAEs featuring a large…

Due to the publicly available thematic maps and crowd-sourced data, remote sensing (RS) image annotations can be gathered at zero cost for training deep neural networks (DNNs). However, such annotation sources may increase the risk of…

3D image reconstruction from a limited number of 2D images has been a long-standing challenge in computer vision and image analysis. While deep learning-based approaches have achieved impressive performance in this area, existing deep…

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational costs to consider…

The autoencoder is an unsupervised learning paradigm that aims to create a compact latent representation of data by minimizing the reconstruction loss. However, it tends to overlook the fact that most data (images) are embedded in a…

Coded Aperture Snapshot Spectral Imaging (CASSI) reconstruction aims to recover the 3D spatial-spectral signal from 2D measurement. Existing methods for reconstructing Hyperspectral Image (HSI) typically involve learning mappings from a 2D…

Discriminative features extracted from the sparse coding model have been shown to perform well for classification. Recent deep learning architectures have further improved reconstruction in inverse problems by considering new dense priors…

Whole-slide images (WSIs) are fundamental for computational pathology, where accurate lesion segmentation is critical for clinical decision making. Existing methods partition WSIs into discrete patches, disrupting spatial continuity and…

Objects are composed of a set of geometrically organized parts. We introduce an unsupervised capsule autoencoder (SCAE), which explicitly uses geometric relationships between parts to reason about objects. Since these relationships do not…

Texture analysis is a classical yet challenging task in computer vision for which deep neural networks are actively being applied. Most approaches are based on building feature aggregation modules around a pre-trained backbone and then…

In this work, we explore regions as a potential visual analogue of words for self-supervised image representation learning. Inspired by Masked Autoencoding (MAE), a generative pre-training baseline, we propose masked region autoencoding to…

Implicit neural representations have emerged as a powerful tool in learning 3D geometry, offering unparalleled advantages over conventional representations like mesh-based methods. A common type of INR implicitly encodes a shape's boundary…

Person re-identification (reID) aims to match person images to retrieve the ones with the same identity. This is a challenging task, as the images to be matched are generally semantically misaligned due to the diversity of human poses and…