Low-light image enhancement (LLIE) investigates how to improve the brightness of an image captured in illumination-insufficient environments. The majority of existing methods enhance low-light images in a global and uniform manner, without taking into account the semantic information of different regions. Consequently, a network may easily deviate from the original color of local regions. To address this issue, we propose a semantic-aware knowledge-guided framework (SKF) that can assist a low-light enhancement model in learning rich and diverse priors encapsulated in a semantic segmentation model. We concentrate on incorporating semantic knowledge from three key aspects: a semantic-aware embedding module that adaptively integrates semantic priors in feature representation space, a semantic-guided color histogram loss that preserves color consistency of various instances, and a semantic-guided adversarial loss that produces more natural textures by semantic priors. Our SKF is appealing in acting as a general framework in the LLIE task. We further present a refined framework SKF++ with two new techniques: (a) Extra convolutional branch for intra-class illumination and color recovery through extracting local information and (b) Equalization-based histogram transformation for contrast enhancement and high dynamic range adjustment. Extensive experiments on various benchmarks of LLIE task and other image processing tasks show that models equipped with the SKF/SKF++ significantly outperform the baselines and our SKF/SKF++ generalizes to different models and scenes well. Besides, the potential benefits of our method in face detection and semantic segmentation in low-light conditions are discussed.

Due to the lack of known therapeutic targets for triple-negative breast cancer (TNBC), chemotherapy is the only available pharmacological treatment. Pirarubicin (tetrahydropyranyl Adriamycin, THP) is the most commonly used anthracycline chemotherapy agent. However, TNBC has a high recurrence rate after chemotherapy, and the mechanisms of chemoresistance and recurrence are not entirely understood. To study the chemoresistance mechanisms, we first screened compounds on a pirarubicin-resistant cell line (MDA-MB-231R) derived from MDA-MB-231. The drug resistance index of MDA-MB-231R cells was approximately five times higher than that of MDA-MB-231 cells. MDA-MB-231R cells have higher GRP78 and lower miR-495-3p expression levels than MDA-MB-231 cells. Transfecting MDA-MB-231R cells with a siGRP78 plasmid reduced GRP78 expression, which restored pirarubicin sensitivity. Besides, transfecting MDA-MB-231R cells with miR-495-3p mimics increased miR-495-3p expression, which also reversed pirarubicin chemoresistance. Cell counting kit-8 (CCK-8), EdU, wound healing and Transwell assays showed that the miR-495-3p mimics also inhibited cell proliferation and migration. Based on our results, miR-495-3p mimics could down-regulate GRP78 expression viathe p-AKT/mTOR signaling pathway in TNBC cells. Remarkably, chemo-resistant and chemo-sensitive TNBC tissues had opposite trends in GRP78 and miR-495-3p expressions. The lower the GRP78 and the higher the miR-495-3p expression, the better prognosis in TNBC patients. Therefore, the mechanism of pirarubicin resistance might involve the miR-495-3p/GRP78/Akt axis, which would provide a possible strategy for treating TNBC.

Supervised dehazing models, trained on synthetic hazy-clean image pairs, often face a notable decline in performance when applied to real-world scenes. Consequently, CycleGAN-based unpaired dehazing methods are proposed to improve the model’s generalization. One successful approach among these methods involves decomposing the physical properties of the atmospheric scattering model (ASM). However, estimating physical properties individually from input images is difficult without supervised labels, which ignores the semantic consistency between different physical regions. We claim semantic region information can offer additional geometric spatial constraints for estimating physical properties, as natural images can be divided into regions with similar scene depths. Motivated by this, we propose a novel generalized and realistic unpaired image dehazing framework via region-aware physical constraints (RPC-Dehaze). Our approach utilizes fine-grained semantic region maps from the Segment Anything Model (SAM) in a specially designed region prompt enhancement module. This enables the dehazing and hazing cyclic networks to learn region-aware physical constraints, leading to accurate estimation of haze imaging physical properties. In contrast to existing unpaired methods that treat dehazing and hazing networks equally, we incorporate Retinex theory into the hazing network, allowing it to learn diverse illumination effects in different regions. We adaptively refine the Retinex-based illumination component, resulting in more realistic hazy images. To further facilitate unsupervised learning in our framework, we propose a physical consensual contrastive regularization to ensure compact representation constraints in the latent feature space. Extensive experiments on synthetic and real image datasets show our method surpasses state-of-the-art unpaired dehazing methods in both effectiveness and generalization capability.

Low-light image enhancement (LLIE) has achieved promising performance by employing conditional diffusion models. Despite the success of some conditional methods, previous methods may neglect the importance of a sufficient formulation of task-specific condition strategy, resulting in suboptimal visual outcomes. In this study, we propose JoReS-Diff, a novel approach that incorporates Retinex- and semantic-based priors as the additional pre-processing condition to regulate the generating capabilities of the diffusion model. We first leverage pre-trained decomposition network to generate the Retinex prior, which is updated with better quality by an adjustment network and integrated into a refinement network to implement Retinex-based conditional generation at both feature- and image-levels. Moreover, the semantic prior is extracted from the input image with an off-the-shelf semantic segmentation model and incorporated through semantic attention layers. By treating Retinex- and semantic-based priors as the condition, JoReS-Diff presents a unique perspective for establishing an diffusion model for LLIE and similar image enhancement tasks. Extensive experiments validate the rationality and superiority of our approach.

When applying high-level visual algorithms to rainy scenes, it is customary to preprocess the rainy images using low-level rain removal networks, followed by visual networks to achieve the desired objectives. Such a setting has never been explored by adversarial attack methods, which are only limited to attacking one kind of them. Considering the deficiency of multi-functional attacking strategies and the significance for open-world perception scenarios, we are the first to propose a Cascaded Adversarial Attack (CAA) setting, where the adversarial example can simultaneously attack different-level tasks, such as rain removal and semantic segmentation in an integrated system. Specifically, our attack on the rain removal network aims to preserve rain streaks in the output image, while for the semantic segmentation network, we employ powerful existing adversarial attack methods to induce misclassification of the image content. Importantly, CAA innovatively utilizes binary masks to effectively concentrate the aforementioned two significantly disparate perturbation distributions on the input image, enabling attacks on both networks. Additionally, we propose two variants of CAA, which minimize the differences between the two generated perturbations by introducing a carefully designed perturbation interaction mechanism, resulting in enhanced attack performance. Extensive experiments validate the effectiveness of our methods, demonstrating their superior ability to significantly degrade the performance of the downstream task compared to methods that solely attack a single network.

Hand-object occlusion is crucial to enhance the realism of Aug-mented Reality, especially for egocentric hand-object interaction scenes. In this paper, a hand segmentation-based depth correction approach is proposed, which can help to realize real-time hand-object occlusion. We introduce a lightweight convolutional neural net-work to quickly obtain real hand segmentation mask. Based on the hand mask, different strategies are adopted to correct the depth data of hand and non-hand regions, which can implement hand-object occlusion and object-object occlusion simultaneously to deal with complex hand situations during interaction. The experimental re-sults demonstrate the feasibility of our approach presenting visually appealing occlusion effects.