Search

Single image dehazing is a challenging ill-posed problem that has drawn significant attention in the last few years. Recently, convolutional neural networks have achieved great success in image dehazing. However, it is still difficult for these increasingly complex models to recover accurate details from the hazy image. In this paper, we pay attention to the feature extraction and utilization of the input image itself. To achieve this, we propose a Multi-scale Topological Network (MSTN) to fully explore the features at different scales. Meanwhile, we design a Multi-scale Feature Fusion Module (MFFM) and an Adaptive Feature Selection Module (AFSM) to achieve the selection and fusion of features at different scales, so as to achieve progressive image dehazing. This topological network provides a large number of search paths that enable the network to extract abundant image features as well as strong fault tolerance and robustness. In addition, ASFM and MFFM can adaptively select important features and ignore interference information when fusing different scale representations. Extensive experiments are conducted to demonstrate the superiority of our method compared with state-of-the-art methods.

Image denoising is a challenging inverse problem due to complex scenes and information loss. Recently, various methods have been considered to solve this problem by building a well-designed convolutional neural network (CNN) or introducing some hand-designed image priors. Different from previous works, we investigate a new framework for image denoising, which integrates edge detection, edge guidance, and image denoising into an end-to-end CNN model. To achieve this goal, we propose a multilevel edge features guided network (MLEFGN). First, we build an edge reconstruction network (Edge-Net) to directly predict clear edges from the noisy image. Then, the Edge-Net is embedded as part of the model to provide edge priors, and a dual-path network is applied to extract the image and edge features, respectively. Finally, we introduce a multilevel edge features guidance mechanism for image denoising. To the best of our knowledge, the Edge-Net is the first CNN model specially designed to reconstruct image edges from the noisy image, which shows good accuracy and robustness on natural images. Extensive experiments clearly illustrate that our MLEFGN achieves favorable performance against other methods and plenty of ablation studies demonstrate the effectiveness of our proposed Edge-Net and MLEFGN. The code is available at https://github.com/MIVRC/MLEFGN-PyTorch .

Image stitching aims to generate a natural seamless high-resolution panoramic image free of distortions or artifacts as fast as possible. In this article, we propose a new seam cutting strategy based on superpixels for unmanned aerial vehicle (UAV) image stitching. Explicitly, we decompose the issue into three steps: image registration, seam cutting, and image blending. First, we employ adaptive as-natural-as-possible (AANAP) warps for registration, obtaining two aligned images in the same coordinate system. Then, we propose a novel superpixel-based energy function that integrates color difference, gradient difference, and texture complexity information to search a perceptually optimal seam located in continuous areas with high similarity. We apply the graph cut algorithm to solve the problem and thereby conceal artifacts in the overlapping area. Finally, we utilize a superpixel-based color blending approach to eliminate visible seams and achieve natural color transitions. Experimental results demonstrate that our method can effectively and efficiently realize seamless stitching, and is superior to several state-of-the-art methods in UAV image stitching.

Low-light image enhancement based on deep convolutional neural networks (CNNs) has revealed prominent performance in recent years. However, it is still a challenging task since the underexposed regions and details are always imperceptible. Moreover, deep learning models are always accompanied by complex structures and enormous computational burden, which hinders their deployment on mobile devices. To remedy these issues, in this paper, we present a lightweight and efficient Luminance-aware Pyramid Network (LPNet) to reconstruct normal-light images in a coarse-to-fine strategy. The architecture is comprised of two coarse feature extraction branches and a luminance-aware refinement branch with an auxiliary subnet learning the luminance map of the input and target images. Besides, we propose a multi-scale contrast feature block (MSCFB) that involves channel split, channel shuffle strategies, and contrast attention mechanism. MSCFB is the essential component of our network, which achieves an excellent balance between image quality and model size. In this way, our method can not only brighten up low-light images with rich details and high contrast but also significantly ameliorate the execution speed. Extensive experiments demonstrate that our LPNet outperforms state-of-the-art methods both qualitatively and quantitatively.

Most modern satellites can provide two types of images: 1) panchromatic (PAN) image and 2) multispectral (MS) image. The former has high spatial resolution and low spectral resolution, while the latter has high spectral resolution and low spatial resolution. To obtain images with both high spectral and spatial resolution, pansharpening has emerged to fuse the spatial information of the PAN image and the spectral information of the MS image. However, most pansharpening methods fail to preserve spatial and spectral information simultaneously. In this article, we propose a framelet-based convolutional neural network (CNN) for pansharpening which makes it possible to pursue both high spectral and high spatial resolution. Our network consists of three subnetworks: 1) feature embedding net; 2) feature fusion net; and 3) framelet prediction net. Different from conventional CNN methods directly inferring high-resolution MS images, our approach learns to predict their framelet coefficients from available PAN and MS images. The introduction of multilevel feature aggregation and hybrid residual connection makes full use of spatial information of PAN image and spectral information of MS image. Quantitative and qualitative experiments at reduced- and full-resolution demonstrate that the proposed method achieves more appealing results than other state-of-the-art pansharpening methods. The source code and trained models are available at https://github.com/TingMAC/FrMLNet.

In this paper, we investigate the challenging task of removing haze from a single natural image. The analysis on the haze formation model shows that the atmospheric veil has much less relevance to chrominance than luminance, which motivates us to neglect the haze in the chrominance channel and concentrate on the luminance channel in the dehazing process. Besides, the experimental study illustrates that the YUV color space is most suitable for image dehazing. Accordingly, a variational model is proposed in the Y channel of the YUV color space by combining the reformulation of the haze model and the two effective priors. As we mainly focus on the Y channel, most of the chrominance information of the image is preserved after dehazing. The numerical procedure based on the alternating direction method of multipliers (ADMM) scheme is presented to obtain the optimal solution. Extensive experimental results on real-world hazy images and synthetic dataset demonstrate clearly that our method can unveil the details and recover vivid color information, which is competitive among many existing dehazing algorithms. Further experiments show that our model also can be applied for image enhancement.

Interference between the grids of the camera sensor and the screen cause moire patterns to always appear on photographs captured from a screen, significantly affecting people’s ability to review images. We propose a novel method to remove such a screen moire pattern from a single image. We characterize the degraded image as a composition of two layers: the latent layer and the moire pattern layer. Because the screen moire pattern is global and content-independent, we regard it as a group of sublayers , and we find that each sublayer after the shear transformation has a low-rank property . Combined with the piecewise constant feature of the latent layer, a convex model is proposed to solve the demoireing problem. Experiments on synthetic and real data demonstrate its feasibility and efficiency.

In this paper, we propose a novel Retinex-based fractional-order variational model for severely low-light images. The proposed method is more flexible in controlling the regularization extent than the existing integer-order regularization methods. Specifically, we decompose directly in the image domain and perform the fractional-order gradient total variation regularization on both the reflectance component and the illumination component to get more appropriate estimated results. The merits of the proposed method are as follows: 1) small-magnitude details are maintained in the estimated reflectance. 2) illumination components are effectively removed from the estimated reflectance. 3) the estimated illumination is more likely piecewise smooth. We compare the proposed method with other closely related Retinex-based methods. Experimental results demonstrate the effectiveness of the proposed method.

The task of single image super-resolution (SISR) is a highly ill-posed inverse problem since reconstructing the high-frequency details from a low-resolution image is challenging. Most previous CNN-based super-resolution (SR) methods tend to directly learn the mapping from the low-resolution image to the high-resolution image through some complex convolutional neural networks. However, the method of blindly increasing the depth of the network is not the best choice because the performance improvement of such methods is marginal but the computational cost is huge. A more efficient method is to integrate the image prior knowledge into the model to assist the image reconstruction. Indeed, the soft-edge has been widely applied in many computer vision tasks as the role of an important image feature. In this paper, we propose a Soft-edge assisted Network (SeaNet) to reconstruct the high-quality SR image with the help of image soft-edge. The proposed SeaNet consists of three sub-nets: a rough image reconstruction network (RIRN), a soft-edge reconstruction network (Edge-Net), and an image refinement network (IRN). The complete reconstruction process consists of two stages. In Stage-I, the rough SR feature maps and the SR soft-edge are reconstructed by the RIRN and Edge-Net, respectively. In Stage-II, the outputs of the previous stages are fused and then fed to the IRN for high-quality SR image reconstruction. Extensive experiments show that our SeaNet converges rapidly and achieves excellent performance under the assistance of image soft-edge. The code is available at https://gitlab.com/junchenglee/seanet-pytorch .

Blind deblurring has received considerable attention in recent years. However, state-of-the-art methods often fail to process saturated blurry images. The main reason is that pixels around saturated regions are not conforming to the commonly used linear blur model. Pioneer arts suggest excluding these pixels during the deblurring process, which sometimes simultaneously removes the informative edges around saturated regions and results in insufficient information for kernel estimation when large saturated regions exist. To address this problem, we introduce a new blur model to fit both saturated and unsaturated pixels, and all informative pixels can be considered during the deblurring process. Based on our model, we develop an effective maximum a posterior (MAP)-based optimization framework. Quantitative and qualitative evaluations on benchmark datasets and challenging real-world examples show that the proposed method performs favorably against existing methods.

Deblurring night blurry images is difficult, because the common-used blur model based on the linear convolution operation does not hold in this situation due to the influence of saturated pixels. In this paper, we propose a non-blind deblurring network (NBDN) to restore night blurry images. To mitigate the side effects brought by the pixels that violate the blur model, we develop a confidence estimation unit (CEU) to estimate a map which ensures smaller contributions of these pixels in the deconvolution steps which are optimized by the conjugate gradient (CG) method. Moreover, unlike the existing methods using manually tuned hyper-parameters in their frameworks, we propose a hyper-parameter estimation unit (HPEU) to adaptively estimate hyper-parameters for better image restoration. The experimental results demonstrate that the proposed network performs favorably against state-of-the-art algorithms both quantitatively and qualitatively.

Pan-sharpening is a method of integrating low-resolution multispectral images with corresponding high-resolution panchromatic images to obtain multispectral images with high spectral and spatial resolution. A novel variational model for pan-sharpening is proposed in this paper. The model is mainly based on three hypotheses: 1) the pan-sharpened image can be linearly represented by the corresponding panchromatic image; 2) the low-resolution multispectral image is down-sampled from the highresolution multispectral image through the down-sampling operator; and 3) the satellite image has the low-rank property. Three energy components corresponding to these assumptions are integrated into a variational framework to obtain a total energy function. We adopt the alternating direction method of multipliers (ADMM) to optimize the total energy function. The experimental results show that the proposed method performs better than other mainstream methods in spectral and spatial information preserving aspect.

In this letter, we propose a fast and robust method for stitching overlapped images captured by the unmanned aerial vehicle. First, we apply the shape-preserving half-projective method to precisely and stably align a pair of partially overlapped input images. Then, an optimal stitching line is searched to remove ghosts caused by the moving objects in the overlapped area. We subsequently propose a color blending method to eliminate all the color inconsistencies in the prealigned image. In accordance with the color differences of the pixels on the optimal stitching seam, we utilize weighted value coordinate interpolation algorithms to compute accurate color changes for all the pixels in the target image. The calculated color changes are then added to the target image to remove the color inconsistency. Furthermore, we introduce the superpixel segmentation to divide the target image into a reduced number of superpixels, and we assign each superpixel the same color change value. Such a superpixel level operation can greatly reduce the computational complexity. Experiments show that our method is promising to achieve effective and efficient stitching results.

Cervical cancer is one of the leading causes of female-specific cancer death. Tumor region segmentation plays a pivotal role in both the clinical analysis and treatment planning of cervical cancer. Due to the heterogeneity and low contrast of biomedical images, current state-of-the-art tumor segmentation approaches are facing the challenge of the insensitive detection of small lesion regions. To tackle this problem, this paper proposes an augmented multiscale network (AugMS-Net) based on 3D U-Net to automatically segment cervical Magnetic Resonance Imaging (MRI) volumes. Since a multiscale strategy is considered one of the most promising algorithms to tackle small object recognition, we introduce a novel 3D module to explore more granular multiscale representations. Besides, we employ a deep multiscale supervision strategy to doubly supervise the side outputs hierarchically. To demonstrate the generalization of our model, we evaluated AugMS-Net on both a cervical dataset from MRI volumes and a liver dataset from Computerized Tomography (CT) volumes. Our proposed AugMS-Net shows superior performance over baseline models, yielding high accuracy while reducing the number of model parameters by nearly 20%. The source code and trained models are available at https://github.com/Cassieyy/AugMS-Net.

Under stereo settings, the problem of image super-resolution (SR) and disparity estimation are interrelated that the result of each problem could help to solve the other. The effective exploitation of correspondence between different views facilitates the SR performance, while the high-resolution (HR) features with richer details benefit the correspondence estimation. According to this motivation, we propose a Stereo Super-Resolution and Disparity Estimation Feedback Network (SSRDE-FNet), which simultaneously handles the stereo image super-resolution and disparity estimation in a unified framework and interact them with each other to further improve their performance. Specifically, the SSRDE-FNet is composed of two dual recursive sub-networks for left and right views. Besides the cross-view information exploitation in the low-resolution (LR) space, HR representations produced by the SR process are utilized to perform HR disparity estimation with higher accuracy, through which the HR features can be aggregated to generate a finer SR result. Afterward, the proposed HR Disparity Information Feedback (HRDIF) mechanism delivers information carried by HR disparity back to previous layers to further refine the SR image reconstruction. Extensive experiments demonstrate the effectiveness and advancement of SSRDE-FNet.

Convolutional neural networks have been proven to be of great benefit for single-image super-resolution (SISR). However, previous works do not make full use of multi-scale features and ignore the inter-scale correlation between different upsampling factors, resulting in sub-optimal performance. Instead of blindly increasing the depth of the network, we are committed to mining image features and learning the inter-scale correlation between different upsampling factors. To achieve this, we propose a Multi-scale Dense Cross Network (MDCN), which achieves great performance with fewer parameters and less execution time. MDCN consists of multi-scale dense cross blocks (MDCBs), hierarchical feature distillation block (HFDB), and dynamic reconstruction block (DRB). Among them, MDCB aims to detect multi-scale features and maximize the use of image features flow at different scales, HFDB focuses on adaptively recalibrate channel-wise feature responses to achieve feature distillation, and DRB attempts to reconstruct SR images with different upsampling factors in a single model. It is worth noting that all these modules can run independently. It means that these modules can be selectively plugged into any CNN model to improve model performance. Extensive experiments show that MDCN achieves competitive results in SISR, especially in the reconstruction task with multiple upsampling factors. The code will be provided at https://github.com/MIVRC/MDCN-PyTorch., 15 pages, 15 figures

Exemplar-based colorization aims to add colors to a grayscale image guided by a content related reference im- age. Existing methods are either sensitive to the selection of reference images (content, position) or extremely time and resource consuming, which limits their practical applica- tion. To tackle these problems, we propose a deep exemplar colorization architecture inspired by the characteristics of stylization in feature extracting and blending. Our coarse- to-fine architecture consists of two parts: a fast transfer sub-net and a robust colorization sub-net. The transfer sub- net obtains a coarse chrominance map via matching basic feature statistics of the input pairs in a progressive way. The colorization sub-net refines the map to generate the final re- sults. The proposed end-to-end network can jointly learn faithful colorization with a related reference and plausible color prediction with unrelated reference. Extensive exper- imental validation demonstrates that our approach outper- forms the state-of-the-art methods in less time whether in exemplar-based colorization or image stylization tasks.

Existing arts have shown promising efforts to deal with the blind deblurring task. However, most of the recent works assume the additive noise involved in the blurring process to be simple-distributed (i.e. Gaussian or Laplacian), while the real-world case is proved to be much more complicated. In this paper, we develop a new term to better fit the complex natural noise. Specifically, we use a combination of a dense function (i.e. \(l_2\)) and a newly designed enhanced sparse model termed as \(l_e\), which is developed from two sparse models (i.e. \(l_1\) and \(l_0\)), to fulfill the task. Moreover, we further suggest using \(l_e\) to regularize image gradients. Compared to the widely-adopted \(l_0\) sparse term, \(l_e\) can penalize more insignificant image details (Fig. 1). Based on the half-quadratic splitting method, we provide an effective scheme to optimize the overall formulation. Comprehensive evaluations on public datasets and real-world images demonstrate the superiority of the proposed method against state-of-the-art methods in terms of both speed and accuracy.

Panorama creation is still challenging in consumer-level photography because of varying conditions of image capturing. A long-standing problem is the presence of artifacts caused by structure inconsistent image transitions. Since it is difficult to achieve perfect alignment in unconstrained shooting environment especially with parallax and object movements, image composition becomes a crucial step to produce artifact-free stitching results. Current energy-based seam-cutting image composition approaches are limited by the hand-crafted features, which are not discriminative and adaptive enough to robustly create structure consistent image transitions. In this paper, we present the first end-to-end deep learning framework named Edge Guided Composition Network (EGCNet) for the composition stage in image stitching. We cast the whole composition stage as an image blending problem, and aims to regress the blending weights to seamlessly produce the stitched image. To better preserve the structure consistency, we exploit perceptual edges to guide the network with additional geometric prior. Specifically, we introduce a perceptual edge branch to integrate edge features into the model and propose two edge-aware losses for edge guidance. Meanwhile, we gathered a general-purpose dataset for image stitching training and evaluation (namely, RISD). Extensive experiments demonstrate that our EGCNet produces plausible results with less running time, and outperforms traditional methods especially under the circumstances of parallax and object motions.