8 July 2020 in IEEE Transactions on Multimedia
Existing discriminative learning methods for image denoising use either a single residual learning or a nonresidual learning design. However, we observe that these two schemes perform differently with the same noise level, and yet, there have been no explorations regarding whether residual or nonresidual designs are better suited for denoising. Additionally, many discriminative denoisers are designed to learn a model that corresponds to a fixed noise level, which means that multiple models are required to recover corrupted images with noise at different levels. In this paper, we propose a dynamic dual learning network for blind image denoising, namely, DualBDNet. Instead of modeling a sole task prediction network, the proposed DualBDNet investigates the inherent relations between the residual estimation and the nonresidual estimation. In particular, DualBDNet produces task-dependent feature maps, and each part of the features is devoted to one specific task (residual/nonresidual mapping). To address different noise levels with a single network or even cases where the statistics of noise are unknown, we further introduce an embedded subnetwork into DualBDNet. One output of the subnetwork is the learning of a dynamic compositional attention to highlight the more significant task-dependent feature maps, adaptively coinciding with the extent of corruption. The other output is the learning of a weight used for fusion of the results to ensure an end-to-end manner. Extensive experiments demonstrate that the proposed DualBDNet outperforms the state-of-the-art methods on both synthetic and real noisy images without estimating the noise levels as input.
19 April 2021 in IEEE Signal Processing Letters
Shadow removal is an important yet challenging task in image processing and computer vision. Existing methods are limited in extracting good global features due to the interference of shadow. And also, most of them ignore a fact that features inside and outside the shaded area should be treated disparately because of different semantics or materials. In this letter, we propose a novel deep neural network Mask-ShadowNet for shadow removal. The core of our approach is a well-designed masked adaptive instance normalization (MAdaIN) mechanism with embedded aligners that serves two goals: 1) producing hidden features that considering an illumination consistency of different regions. 2) treating the feature statistics of shadow and non-shadow areas discriminately based on the shadow mask. Experimental results demonstrate that the proposed model outperforms the state-of-the-art on the ISTD benchmark. Our code is available in https://github.com/penguinbing/Mask-ShadowNet.
6 March 2023 in Computer Vision and Image Understanding
24 July 2018 in IEEE Transactions on Cybernetics
In the era of data science, a huge amount of data has emerged in the form of tensors. In many applications, the collected tensor data are incomplete with missing entries, which affects the analysis process. In this paper, we investigate a new method for tensor completion, in which a low-rank tensor approximation is used to exploit the global structure of data, and sparse coding is used for elucidating the local patterns of data. Regarding the characterization of low-rank structures, a weighted nuclear norm for the tensor is introduced. Meanwhile, an orthogonal dictionary learning process is incorporated into sparse coding for more effective discovery of the local details of data. By simultaneously using the global patterns and local cues, the proposed method can effectively and efficiently recover the lost information of incomplete tensor data. The capability of the proposed method is demonstrated with several experiments on recovering MRI data and visual data, and the experimental results have shown the excellent performance of the proposed method in comparison with recent related methods.
29 January 2021 in Wireless Communications and Mobile Computing
An efficient and low‐cost communication system has great significance in maritime communication, but it faces enormous challenges because of high communication costs, incomplete communication infrastructure, and inefficient routing algorithms. Delay Tolerant Vessel Networks (DTVNs), which can create low‐cost communication opportunities among vessels, have recently attracted considerable attention in the academic community. Most existing maritime ad hoc routing algorithms focus on predicting vessels’ future contacts by mining coarse‐grained social relations or spatial distribution, which has led to poor performance. In this paper, we analyze 3‐year trajectory data of 5123 fishery vessels in the China East Sea. Using entropy theory, we observe that the trajectory of the vessel has strongly spatial‐temporal distribution regularity, especially when previous states were given. To predict accurate future trajectories, we develop a long‐term accurate trajectory prediction model by improving the Bidirectional Long‐Short Term Memory (Bi‐LSTM) model. Based on predicted trajectories and the confident degree of each prediction step, we propose a series of routing algorithms called TPR‐DTVN to achieve efficient communication performance. Finally, we carry out simulation experiments with extensive real data. Compared with existing algorithms, the simulation results show that TPR‐DTVN can achieve a higher delivery ratio with lower cost and transmission delay.
11 January 2022 in IEEE Transactions on Image Processing
The state-of-the-art photo upsampling method, PULSE, demonstrates that a sharp, high-resolution (HR) version of a given low-resolution (LR) input can be obtained by exploring the latent space of generative models. However, mapping an extreme LR input (16 2 ) directly to an HR image (1024 2 ) is too ambiguous to preserve faithful local facial semantics. In this paper, we propose an enhanced upsampling approach, Pro-PULSE, that addresses the issues of semantic inconsistency and optimization complexity. Our idea is to learn an encoder that progressively constructs the HR latent codes in the extended $\mathcal {W}+$ latent space of StyleGAN. This design divides the complex $64\times $ upsampling problem into several steps, and therefore small-scale facial semantics can be inherited from one end to the other. In particular, we train two encoders, the base encoder maps latent vectors in $\mathcal {W}$ space and serves as a foundation of the HR latent vector, while the second scale-specific encoder performed in $\mathcal {W}+$ space gradually replaces the previous vector produced by the base encoder at each scale. This process produces intermediate side-outputs, which injects deep supervision into the training of encoder. Extensive experiments demonstrate superiorities over the latest latent space exploration methods, in terms of efficiency, quantitative quality metrics, and qualitative visual results.