Although the detection accuracy of RGB-D salient object detection by deep learning has met most of the task requirements, it is still a challenge to predict complete salient objects under the guidance of poor depth maps. In this paper, edge prior and depth prior are utilized to guide the network to detect salient objects, and a novel dual priors network called DPNet is proposed for RGB-D SOD. DPNet utilizes edge priors to compensate for the inadequate guidance of low-quality depth maps. Specially, the input RGB and depth maps are encoded by ResNet-50 backbone. To fuse these information effectively, multi-modal feature fusion module downsamples high-resolution features to enhance low-resolution features with its rich semantic information. Then the initial salient masks are decoded by a coarse-grained mask decoder. In addition, edge prior serves as label and is captured by an edge aware module. Finally, the fine-grained salient masks are obtained by fusing the initial salient masks and the salient edges. The experimental results on six benchmarks indicate that the proposed method outperforms ten state-of-the-art methods in six evaluation metrics.

Image dehazing using learning-based methods has achieved state-of-the-art performance in recent years. However, most of previous models for low-level vision tasks are always based on single-stage design. There is an issue with majority image dehazing approaches: a complex balance problem between spatial details and high-level contextualized information while recovering images. To address this issue, we propose a two-stage network, which consists of encoder-decoder subnetwork and original-resolution one. Specifically, the encoder-decoder subnetwork first learns the contextualized features, and then the features are combined with the original-resolution subnet that maintains enriched high-resolution features. For information exchange between two stages, we introduce a Cross-Scale Non-Local (CS-NL) attention module that can search more high-frequency details from low-resolution images in encoder-decoder stage and transfer directly them to the next stage. Moreover we embed the spatial feature transform (SFT) module into original-resolution subnet, which is incorporated with depth information to better achieve the purpose of image dehazing. The two-stage network, named as TSDCN-Net, which demonstrates its effectiveness according extensive experiments. The TSDCN-Net surpasses previous state-of-the-art single image dehazing methods by a large margin both quantitatively and qualitatively.

Deep Convolutional Neural Networks (DCNNs) have achieved remarkable performance in single image super-resolution (SISR). However, most SR methods restore high resolution (HR) images from single-scale region in the low resolution (LR) input, which limits the ability of method to infer multi-scales of details for high resolution (HR) output. In this paper a novel basic building block called self-Calibrated residual block (SARB) is proposed to solve this problem. SARB consists of carefully designed multi-scale paths, which can capture rich structure information from different scale. In addition, self-Calibrated residual block is introduced to adaptively learn informatively context to make network generate more discriminative representations. These blocks are composed of self-calibrated attention residual network (SARN) for image super-resolution. Experiments results on five benchmark datasets demonstrate that the proposed SARN achieves comparable results compared with the previous most of the state-of-the-art methods.

This paper have given a nonlocal denoising framework based on tensor robust principal component analysis with ℓpnorm for color image and video (NDFCIV), which have following three features: (1) it is capable of processing zero-mean Gaussian noise, impulse noise and any other noise that is created by mixing the two for color image and video at same time. (2) Meanwhile, nonlocal denoising strategy is adopted to promote the effectiveness of the denoising framework. (3) Moreover, we present a non-convex constraint method which can get more exact low rank tensor recovery result and enhance the denoising effect of the framework further. The experimental results demonstrate the effectiveness of the proposed denoising framework.

Recently, deep neural networks have been widely used in the task of single image super-resolution. However, existing deep neural networks always take huge parameters to map low-resolution images to high-resolution ones. In addition, most of them only consider high-level features to reconstruct high-resolution images. These two methodologies not only cause the difficulty of practical applications but also the inefficiency of restoring image details. Therefore, in this work, the authors propose a novel sparse block to learn high-level features. Based on this block, a fusion method is proposed to fuse features from multiple levels. By incorporating these two approaches, a lightweight neural network, i.e. Sparse Block Fusion Network (SBFN), is proposed for end-to-end training. Through extensive experiments, it is demonstrated the proposed methods can achieve comparable performance with few parameters. By making comprehensive comparisons, effectiveness of SBFN is also verified in multiple benchmark datasets.

Recently, deep convolution neural networks have achieved remarkable performance in the task of single image super-resolution (SISR). However, effectiveness of existing networks highly relies on their receptive field, which always increases with the depth of the network. In this work, we propose a novel module, named as residual group, to effectively learn feature maps by using dynamic receptive field. This residual group firstly uses a selective kernel convolution layer to dynamically learn multi-scale information from its input features. Then, several residual blocks are employed to further refine the learned feature. In addition, we also propose a selective feature fusion module to fuse appearance information in multi-level features. Within this module, the low-level features and high-level features are selectively fused to complement the high-level ones. Finally, by combining these two methods, we introduce a multi-level feature fusion network (MLFFN) for single image super-resolution (SISR). Through comprehensive experiments, we demonstrate that the proposed MLFFN achieves state-of-the-art performance both quantitatively and qualitatively.

Single image haze removal is a challenging ill-posed problem in computer vision. Instead of leveraging the traditional model or handcrafted image priors, an end-to-end multi-scale convolutional neural network is proposed for single image haze removal task by directly mapping the hazy image to its corresponding haze-free image. To better retain the coarse and fine information, a multi-scale block is elaborated and embedded into the proposed architecture. This block can extract the feature at varying scales with a model size that is as small as possible. The global skip connection is adopted to promote the model performance. Extensive experiment results demonstrate that the proposed network outperforms the state-of-the-art single image haze removal algorithms on both synthetical and real-world images. In addition, the size of the model in this paper dominates among the high performance methods based on convolutional neural networks.

In this paper, we propose a new single-image dehazing method for synthetic and real-world hazy images. Based on the color attenuation prior, this proposed dehazing method improves it in two aspects. First, we estimate the atmospheric light with the haze-lines prior, which is based on the observation that pixel values of a hazy image can be modeled as lines in the RGB color space that intersects at the air-light. Second, the dynamic scattering coefficient, which is an exponential function of image depth, is proposed to replace the constant scattering coefficient. Experimental results demonstrate that the dehazed image of proposed algorithm is clearer and more natural than that of the color attenuation prior. The proposed algorithm can effectively improve the effect of dehazing.