Search

Images captured in the low-light condition suffer from low visibility and various imaging artifacts, e.g., real noise. Existing supervised algorithms for low-light image enhancement require a large set of pixel-aligned training image pairs, which are hard to prepare in practice. Though some recent unsupervised methods can alleviate such data challenges, many real world artifacts inevitably get falsely amplified in the enhanced results due to the lack of corresponding supervision. In this paper, instead of using perfectly aligned images for training, we creatively employ the misaligned real world images as the guidance, which are considerably easier to collect. Specifically, we propose a Cross-Image Disentanglement Network (CIDN) with weakly supervised learning, to separately extract cross-image brightness and image-specific content features from low/normal-light images. Based on that, CIDN can simultaneously correct the brightness and suppress image artifacts in the feature domain, which largely increases the robustness of the pixel shifts between training pairs. By considering real world corruptions, we propose a new training dataset with misaligned and noisy image pairs and its corresponding evaluation dataset. Experimental results show that our model achieves state-of-the-art performances on both the newly proposed dataset and other popular low-light datasets. The code implementation is publicly available at: https://github.com/GuoLanqing/CIDN.

In heavy rain video, rain streak and rain accumulation are the most common causes of degradation. They occlude background information and can significantly impair the visibility. Most existing methods rely heavily on the synthetic training data, and thus raise the domain gap problem that prevents the trained models from performing adequately in real testing cases. Unlike these methods, we introduce a self-learning method to remove both rain streaks and rain accumulation without using any ground-truth clean images in training our model, which consequently can alleviate the domain gap issue. The main idea is based on the assumptions that (1) adjacent clean frames can be aligned or warped from one frame to another frame, (2) rain streaks are distributed randomly in the temporal domain, (3) the rain streak/accumulation related variables/priors can be inferred reliably from the information within the images/sequences. Based on these assumptions, we construct an augmented Self-Learned Deraining Network (SLDNet+) to remove both rain streaks and rain accumulation by utilizing temporal correlation, consistency, and rain-related priors. For the temporal correlation, our SLDNet+ takes rain degraded adjacent frames as its input, aligns them, and learns to predict the clean version of the current frame. For the temporal consistency, a new loss is designed to build a robust mapping between the predicted clean frame and non-rain regions from the adjacent rain frames. For the rain-streak-related prior, the rain streak removal network is optimized jointly with motion estimation and rain region detection; while for the rain-accumulation-related prior, a novel non-local video rain accumulation removal method is developed to estimate the accumulation-lines from the whole input video and to offer better color constancy and temporal smoothness. Extensive experiments show the effectiveness of our approach, which provides superior results compared with the existing state of the art methods both quantitatively and qualitatively. The source code will be made publicly available at: https://github.com/flyywh/CVPR-2020-Self-Rain-Removal-Journal.

Polyphenol-rich foods have been shown to be good for cancer prevention as powerful antioxidants. In this study, the mechanisms of wild pink bayberry free phenolic extract (WPBFE) inhibiting the proliferation and inducing apoptotic of MDA-MB-231 breast cancer cells was examined. The main phenolic acids and flavonols in WPBFE were gallic acid ((18.83 ± 0.44) μg/g FW) and myricetin ((1.52 ± 0.05) μg/g FW), respectively. The maximum inhibition rate of WPBFE at non-cytotoxicity dose (below 80 mg/mL) was 81 %. Western blotting analysis showed that WPBFE could cause the arrest of cell cycle in G0/G1 phase by down-regulating expression levels of PCNA, CDK4, cyclin D1 and up-regulating the expression level of p21. Meanwhile, WPBFE induced apoptosis through initiating the mitochondrial death pathway by up-regulating cleaved caspase-3 and enhancing the ratio of Bax/Bcl-2, with the maximum expression levels of 1.29 and 2.03 folds that of control group, respectively. Further study of the upstream protein, we found that WPBFE down-regulated TRAF2, while upregulated p-ASK1, p-p38 and p-p53. Furthermore, WPBFE could down-regulate the expression of p-PI3K and p-Akt. These observations indicated that WPBFE might play an anticancer role through regulating the p38 MAPK together with PI3K/Akt pathway.