相关论文: Unsharp Mask Guided Filtering

Guided image restoration (GIR), such as guided depth map super-resolution and pan-sharpening, aims to enhance a target image using guidance information from another image of the same scene. Currently, joint image filtering-inspired deep…

The topic of semantic segmentation has witnessed considerable progress due to the powerful features learned by convolutional neural networks (CNNs). The current leading approaches for semantic segmentation exploit shape information by…

Learning structural information is critical for producing an ideal result in retinal image segmentation. Recently, convolutional neural networks have shown a powerful ability to extract effective representations. However, convolutional and…

Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture rich spatial information, while upper layers encode…

Many remote sensing applications employ masking of pixels in satellite imagery for subsequent measurements. For example, estimating water quality variables, such as Suspended Sediment Concentration (SSC) requires isolating pixels depicting…

Guided image super-resolution (GISR) aims to obtain a high-resolution (HR) target image by enhancing the spatial resolution of a low-resolution (LR) target image under the guidance of a HR image. However, previous model-based methods mainly…

Optical imaging through scattering media is a fundamental challenge in many applications. Recently, substantial breakthroughs such as imaging through biological tissues and looking around corners have been obtained by the use of…

In this paper we propose a new wavelet transform applicable to functions defined on graphs, high dimensional data and networks. The proposed method generalizes the Haar-like transform proposed in [1], and it is defined via a hierarchical…

Single image dehazing is a critical image pre-processing step for subsequent high-level computer vision tasks. However, it remains challenging due to its ill-posed nature. Existing dehazing models tend to suffer from model overcomplexity…

Passive filtering is a common strategy used to reduce airborne disease transmission and particulate contaminants in buildings and individual covers. The engineering of high-performance filters with relatively low flow resistance but high…

The task of classifying mammograms is very challenging because the lesion is usually small in the high resolution image. The current state-of-the-art approaches for medical image classification rely on using the de-facto method for ConvNets…

Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost…

Recent methods for boundary or edge detection built on Deep Convolutional Neural Networks (CNNs) typically suffer from the issue of predicted edges being thick and need post-processing to obtain crisp boundaries. Highly imbalanced…

Deep learning provides a new avenue for image restoration, which demands a delicate balance between fine-grained details and high-level contextualized information during recovering the latent clear image. In practice, however, existing…

Our goal is to provide a review of deep learning methods which provide insight into structured high-dimensional data. Rather than using shallow additive architectures common to most statistical models, deep learning uses layers of…

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

Mask-guided matting networks have achieved significant improvements and have shown great potential in practical applications in recent years. However, simply learning matting representation from synthetic and lack-of-real-world-diversity…

Homography estimation is a basic image alignment method in many applications. It is usually conducted by extracting and matching sparse feature points, which are error-prone in low-light and low-texture images. On the other hand, previous…

We propose a novel model named Multi-Channel Attention Selection Generative Adversarial Network (SelectionGAN) for guided image-to-image translation, where we translate an input image into another while respecting an external semantic…

Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently…