In this paper, we propose a retinex-based decomposition model for a hazy image and a novel end-to-end image dehazing network. In the model, the illumination of the hazy image is decomposed into natural illumination for the haze-free image and residual illumination caused by haze. Based on this model, we design a deep retinex dehazing network (RDN) to jointly estimate the residual illumination map and the haze-free image. Our RDN consists of a multiscale residual dense network for estimating the residual illumination map and a U-Net with channel and spatial attention mechanisms for image dehazing. The multiscale residual dense network can simultaneously capture global contextual information from small-scale receptive fields and local detailed information from large-scale receptive fields to precisely estimate the residual illumination map caused by haze. In the dehazing U-Net, we apply the channel and spatial attention mechanisms in the skip connection of the U-Net to achieve a trade-off between overdehazing and underdehazing by automatically adjusting the channel-wise and pixel-wise attention weights. Compared with scattering model-based networks, fully data-driven networks, and prior-based dehazing methods, our RDN can avoid the errors associated with the simplified scattering model and provide better generalization ability with no dependence on prior information. Extensive experiments show the superiority of the RDN to various state-of-the-art methods.

In recent years, multispectral pedestrian detection as a multimodal solution, using visible light and thermal image multimodal information to solve pedestrian detection challenges in low light environments, plays a crucial role. However, most existing methods directly mix the results of the two modalities or by simply integrating the two modality features. This fusion strategy ignores some features that have specific meaning and are important to the detection problem, and lacks reliable comprehensibility. Drawing inspiration from this insight, in this letter, we propose a pedestrian detection method based on the fusion of multimodal edge information extraction and global semantic consistency, aiming to achieve more full use of edge information-assisted guidance multimodal for accurate fusion detection. We first build an edge attention operation module (EAO) to extract pedestrian edge features, and then introduce a global semantic consistency module (GSC) to make full use of edge features to stimulate guidance modality fusion, and improve the modality consistency between visible light and thermal information. By using challenging KAIST and CVC-14 benchmarks, we observed significant improvements compared to previous state-of-the-art methods. Our proposed method not only outperformed existing techniques but also achieved remarkable accuracy and robustness in the challenging domain of pedestrian detection.

For current learning-based single image deraining methods, deraining networks are usually designed based on a simplified linear additive rain model, which may not only cause unreal synthetic rainy images for both training and testing datasets, but also adversely affect the applicability and generality of corresponding networks. In this paper, we use the screen blend model of Photoshop as the nonlinear rainy image decomposition model. Based on this model, we design a novel channel attention U-DenseNet for rain detection and a residual dense block for rain removal. The detection sub-network not only adjusts channel-wise feature responses by our novel channel attention block to pay more attention to learn the rain map, but also combines the context information with the precise localization by the U-DenseNet to promote pixel-wise estimation accuracy. After rain detection, we use the nonlinear model to get a coarse rain-free image, and then introduce a deraining refinement subnetwork consisted of the residual dense block to obtain a fine rain-free image. For training our network, we apply the nonlinear rain model to synthesize a benchmark dataset called as RITD. It contains 3200 triplets of rainy images, rain maps, and clean background images. Our extensive quantitative and qualitative experimental results show that our method outperforms several state-of-the-art methods on both synthetic and real images.

In the field of Remote Sensing Change Detection (RSCD), accurately identifying significant changes between bitemporal images is essential for environmental monitoring, urban planning, and disaster assessment. In recent years, advancements in deep learning for computer vision have transformed RSCD, significantly enhancing its effectiveness. However, existing methods often overlook the importance of depth information, focusing primarily on two-dimensional information. This limits their ability to capture subtle changes and structural details in three-dimensional space. To address these limitations, we introduce ChangeDA—a depth-augmented multi-task network designed to enhance the effectiveness of RSCD. ChangeDA introduces a depth encoder module to extract implicit depth information from optical images, enabling the utilization of 3D structural information without reliance on external data sources. Through the Depth Infusion Module (DIM), depth information is integrated into the dual-temporal feature maps, significantly enhancing the network’s ability to perceive changes in three-dimensional spatial structures. Additionally, ChangeDA includes a Differential Feature Extractor (DFE) tailored to pinpoint differential features between sequential images, and an Adaptive All feature Fusion (AAFF) strategy that significantly improves recognition accuracy and generalization capability through cross-level feature integration. Performance evaluations on four prominent single-modal datasets—LEVIR-CD, S2-Looking, WHU-CD, and SYSU-CD—yielded state-of-the-art F1-scores of 92.27%, 66.42%, 94.12%, and 82.74%, respectively. Furthermore, ChangeDA also achieved outstanding results on the multi-modal 3DCD dataset, with an F1 score of 63.52% in 2D CD and an RMSE of 1.20 in the 3D CD task. These results demonstrate ChangeDA’s robust adaptability across diverse targets and real-world scenarios.