The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the human perception of image quality. As a result, algorithms minimizing these metrics...
Super resolution is the problem of artificially enlarging a low resolution photograph to recover a plausible high resolution version. In the regime of high magnification factors, the problem is dramatically underspecified and many plausible, high resolution images may match a given low resolution image. In particular, traditional super resolution techniques fail in this regime due to the multimodality...
Low-resolution (LR) is a challenging problem in the real world. In order to obtain better performance for low-resolution face recognition (LRFR), this paper employs a novel approach for matching low-resolution images with high resolution (HR) images based on two-dimensional linear discriminant analysis (2D-LDA) and metric learning method. The LR and HR images are transformed into a common space via...
Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-streamed CNN that predicts depth and depth gradients, which are then fused together into an accurate and...
Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing textto- image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) to generate...
Image resolution enhancement for shallow buried small targets is a meaningful step in holographic subsurface penetrating (HSR) imaging process, due to the fact that image results are easily affected by the complex underground environment and the follow-up high-level vision task is hindered. In this paper, we employ super-resolution convolutional neural network (SRCNN) in HSR image resolution enhancement...
Increasingly, iris recognition towards more relaxed conditions has issued a new super-resolution field direction. In this work we evaluate the use of deep learning and transfer learning for single image super resolution applied to iris recognition. For this purpose, we explore if the nature of the images as well as if the pattern from the iris can influence the CNN transfer learning and, consequently,...
The paper presents an approach to localize human body joints in 3D coordinates based on a single low resolution depth image. First a framework to generate a database of 80k realistic depth images from a 3D body model is described. Then data preprocessing and normalization procedure, and DNN and MLP artificial neural networks architectures and training are presented. The robustness against camera distance...
Recent approaches in generative adversarial networks (GANs) can automatically synthesize realistic images from descriptive text. Despite the overall fair quality, the generated images often expose visible flaws that lack structural definition for an object of interest. In this paper, we aim to extend state of the art for GAN-based text-to-image synthesis by improving perceptual quality of generated...
Cross-resolution face recognition tackles the problem of matching face images with different resolutions. Although state-of-the-art convolutional neural network (CNN) based methods have reported promising performances on standard face recognition problems, such models cannot sufficiently describe images with resolution different from those seen during training, and thus cannot solve the above task...
We propose a dialogic system based on a relevance feedback strategy that allows for the semiautomatic synthesis of a facial image that only exists in a user's mind. The user is presented with several facial images and judges whether each one resembles the face that he or she is imagining. Based on the feedback from the user, a set of sample facial images are used to train an Optimum-Path Forest classifying...
Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations. In this paper, we propose a novel end-to-end cascaded network of CNNs to jointly learn crowd count classification and density map estimation. Classifying crowd count into various groups is tantamount to coarsely estimating the total count in the image thereby incorporating a high-level...
In the past decade, Convolutional Neural Networks (CNNs) have been demonstrated successful for object detections. However, the size of network input is limited by the amount of memory available on GPUs. Moreover, performance degrades when detecting small objects. To alleviate the memory usage and improve the performance of detecting small traffic signs, we proposed an approach for detecting small...
In this paper we propose a deep architecture for detecting people attributes (e.g. gender, race, clothing …) in surveillance contexts. Our proposal explicitly deal with poor resolution and occlusion issues that often occur in surveillance footages by enhancing the images by means of Deep Convolutional Generative Adversarial Networks (DCGAN). Experiments show that by combining both our Generative Reconstruction...
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 super-resolution approaches: Stacked Auto-Encoders (SAE) and Convolutional Neural Networks (CNN) with the most possible lightweight structure to achieve fast speed, preserve...
Neighbors embedding is a promising method for single image super-resolution (SR). However, the fixed number of neighbors for different kind of input low resolution (LR) patches may be improper. In addition, the assumption that low resolution space and high resolution (HR) space has similar local geometry leads to improper HR patches are used for reconstruction. In this paper, we propose a novel single...
The external example-driven single image super-resolution (SISR) method that uses a deep convolutional neural network (CNN) has exhibited superior performance as compared to previously developed SISR methods. However, the advantages of jointly using external and internal examples on a deep CNN framework have not been sufficiently investigated. In this letter, we present a novel method for single image...
In this paper, we present a deep learning method for single infrared image stripe noise removal. Our method is denoted as a deep convolutional neural network (CNN) that takes the noisy image as the input and outputs the clean image. The deep CNN consists of two components: 1) image denoising, substantially removing the stripe noise but losing details, 2) image denoising and super resolution, completely...
Recently, Convolutional Neural Network (CNN) based models have achieved great success in Single Image Super-Resolution (SISR). Owing to the strength of deep networks, these CNN models learn an effective nonlinear mapping from the low-resolution input image to the high-resolution target image, at the cost of requiring enormous parameters. This paper proposes a very deep CNN model (up to 52 convolutional...
Learning based approaches have not yet achieved their full potential in optical flow estimation, where their performance still trails heuristic approaches. In this paper, we present a CNN based patch matching approach for optical flow estimation. An important contribution of our approach is a novel thresholded loss for Siamese networks. We demonstrate that our loss performs clearly better than existing...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.