Search

On the one hand, the dehazing task is an illposedness problem, which means that no unique solution exists. On the other hand, the dehazing task should take into account the subjective factor, which is to give the user selectable dehazed images rather than a single result. Therefore, this paper proposes a multi-output dehazing network by introducing illumination controllable ability, called IC-Dehazing. The proposed IC-Dehazing can change the illumination intensity by adjusting the factor of the illumination controllable module, which is realized based on the interpretable Retinex theory. Moreover, the backbone dehazing network of IC-Dehazing consists of a Transformer with double decoders for high-quality image restoration. Further, the prior-based loss function and unsupervised training strategy enable IC-Dehazing to complete the parameter learning process without the need for paired data. To demonstrate the effectiveness of the proposed IC-Dehazing, quantitative and qualitative experiments are conducted on image dehazing, semantic segmentation, and object detection tasks. Code is available at https://github.com/Xiaofeng-life/ICDehazing.

The research on single image dehazing task has been widely explored. However, as far as we know, no comprehensive study has been conducted on the robustness of the well-trained dehazing models. Therefore, there is no evidence that the dehazing networks can resist malicious attacks. In this paper, we focus on designing a group of attack methods based on first order gradient to verify the robustness of the existing dehazing algorithms. By analyzing the general goal of image dehazing task, five attack methods are proposed, which are prediction, noise, mask, ground-truth and input attack. The corresponding experiments are conducted on six datasets with different scales. Further, the defense strategy based on adversarial training is adopted for reducing the negative effects caused by malicious attacks. In summary, this paper defines a new challenging problem for image dehazing area, which can be called as adversarial attack on dehazing networks (AADN). Code is available at https://github.com/guijiejie/AADN.

With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed. In this paper, we provide a comprehensive survey on supervised, semi-supervised, and unsupervised single image dehazing. We first discuss the physical model, datasets, network modules, loss functions, and evaluation metrics that are commonly used. Then, the main contributions of various dehazing algorithms are categorized and summarized. Further, quantitative and qualitative experiments of various baseline methods are carried out. Finally, the unsolved issues and challenges that can inspire the future research are pointed out. A collection of useful dehazing materials is available at \url{https://github.com/Xiaofeng-life/AwesomeDehazing}., Comment: This paper is accepted by ACM Computing Surveys

This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for $\times$2, $\times$3 and $\times$4 scaling factors, respectively. The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications. 452 participants were registered for three tracks in total, and 24 teams submitted their results. They gauge the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.

Low-dose radiation (LDR) has been known to stimulate cell proliferation. The effect of LDR on human bone marrow mesenchymal stem cells (BMSCs), however, remains to be determined. The current study, therefore, aimed to investigate the effect of LDR on human BMSC proliferation and its mechanisms. To accomplish this, human BMSCs were isolated from ribs and cultured with or without exposition to LDR (75 mGy) for 24 h. Cell proliferation was assessed by MTT assay, the cytokines secreted by the BMSCs were quantified by ELISA, and the proteins associated with cell proliferation and cell cycle were evaluated by immunoblot analysis. BMSCs isolated from human ribs were capable of differentiating into osteoblasts and adipocytes. LDR stimulated human BMSC proliferation (0.580 ± 0.106 vs 0.419 ± 0.026 on day 4, P < 0.05; 0.794 ± 0.025 vs 0.689 ± 0.047 on day 7, P < 0.05) and increased S-phase proportion. LDR significantly enhanced the production of SCF, GM-CSF, and IL-11. Moreover, BMSCs modulated T-cell proliferation, and LDR further augmented the modulatory effect of BMSCs on T-cell proliferation. Cell cycle-associated proteins, such as Rb, CDK1, and CDC25B, appeared to mediate the stimulatory effect of LDR on BMSC proliferation. The findings of the current study indicate that physical stimulants, such as LDR, could be used for the large-scale expansion of human BMSCs, and thus may be used for MSC cellular therapy in clinic.