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.
In this paper, we propose a novel face recognition method that embeds the locality-constrained sparse representation in the dictionary learning framework. The shared-specific dictionary learning is employed to explicitly learn class-specific dictionary for each class that captures the most discriminative features of this class, and simultaneously learn a shared dictionary, whose atoms are shared by...
Deep neural networks have advanced many computer vision tasks, because of their compelling capacities to learn from large amount of labeled data. However, their performances are not fully exploited in semantic image segmentation as the scale of training set is limited, where perpixel labelmaps are expensive to obtain. To reduce labeling efforts, a natural solution is to collect additional images from...
Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to collect for certain applications (consider, for example, satellite stereo imaging). The main contribution of our work is a new weakly supervised method for learning...
While recovery of hyperspectral signals from natural RGB images has been a recent subject of exploration, little to no consideration has been given to the camera response profiles used in the recovery process. In this paper we demonstrate that optimal selection of camera response filters may improve hyperspectral estimation accuracy by over 33%, emphasizing the importance of considering and selecting...
An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image. Hitherto, the problem has been addressed through the application of canonical deep learning methods to regress from the image directly to the 3D shape and pose labels. These approaches, however, are problematic from two perspectives. First, they are minimizing the error between 3D shapes...
It has been recently shown that neural networks can recover the geometric structure of a face from a single given image. A common denominator of most existing face geometry reconstruction methods is the restriction of the solution space to some low-dimensional subspace. While such a model significantly simplifies the reconstruction problem, it is inherently limited in its expressiveness. As an alternative,...
Surface reconstruction from a point cloud is a standard subproblem in many algorithms for dense 3D reconstruction from RGB images or depth maps. Methods, performing only local operations in the vicinity of individual points, are very fast, but reconstructed models typically contain lots of holes. On the other hand, regularized volumetric approaches, formulated as a global optimization, are typically...
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. We further generalize this algorithm to multi-layer and multi-branch cases. Our method reduces the accumulated...
As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime. However, taking a quick shot frequently yields a blurry result due to unwanted camera shake during recording or moving objects in the scene. Removing these artifacts from the blurry recordings is a highly ill-posed problem as neither the sharp image nor the...
This paper proposes a classification method based on principal component reconstruction (PCR) for target recognition in synthetic aperture radar (SAR) image. To characterize the SAR image and alleviate the influence of different intensity of the same targets on target recognition, the SAR image is mapped into the principal component space by the principal component analysis with zero mean. In the...
Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-image translation have made much progress recently [7, 8, 21, 12, 4, 18]. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a conditional GAN. However, human labeling is expensive, even impractical, and large quantities of data may not always be available. Inspired by dual...
Recently, the community of style transfer is trying to incorporate semantic information into traditional system. This practice achieves better perceptual results by transferring the style between semantically-corresponding regions. Yet, few efforts are invested to address the computation bottleneck of back-propagation. In this paper, we propose a new framework for fast semantic style transfer. Our...
This paper proposes a deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering. Unlike most other deep learning strategies applied in this context, our approach tackles these challenging problems by estimating edges and reconstructing images using only cascaded convolutional layers arranged such that...
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...
Based on the success of deep neural networks for image recovery, we propose a new paradigm for the compression and decompression of US signals which relies on a stacked denoising autoencoders. The first layer of the network is used to compress the signals and the remaining layers perform the reconstruction. We train the network on simulated US signals and evaluate its quality on images of the publicly...
Obtaining ultrafast images using steered plane wave (PW) imaging remains a challenge due to the trade-off between image quality and frame rate. PW imaging indeed relies on compounding in order to preserve a good image quality, usually using multiple successive emissions, which in turn yields a decrease of the frame rate. As opposed to this classical approach, we propose a new strategy to reduce the...
Compressed sensing (CS) has drawn many interest in the field ultrasound (US) image recovery. It has demonstrated promising results in the recovery of radio-frequency element raw-data [Liebgott et. al. ULTRAS13, Besson et. al. SPARS17]. The objective of such approaches is to recover the raw-data from undersampled random measurements. It is achieved by means of convex optimization or greedy methods...
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...
Recent research in computed tomographic imaging has focused on developing techniques that enable reduction of the X-ray radiation dose without loss of quality of the reconstructed images or volumes. While penalized weighted-least squares (PWLS) approaches have been popular for CT image reconstruction, their performance degrades for very low dose levels due to the inaccuracy of the underlying WLS statistical...
Generative models are widely used for unsupervised learning with various applications, including data compression and signal restoration. Training methods for such systems focus on the generality of the network given limited amount of training data. A less researched type of techniques concerns generation of only a single type of input. This is useful for applications such as constraint handling,...
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.