Detecting objects in foggy scenes remains a persistent challenge, as detectors trained for fair weather often struggle with foggy data due to blurring effects. Previous methods based on domain adaptation, multi-task learning, etc. try to tackle this challenge, but they often fail to achieve an optimal balance between model complexity and accuracy. Hence, we propose a multi-branch pooling information fusion (MPIF) module, which combines local and global information to enhance feature representation with minimal computational overhead. We also design a lightweight multi-scale dehazing network (LMDNet) and utilize the multi-task learning strategy to adaptively incorporate dehazing feature information into the object detection network. Leveraging these core modules with additional design optimizations, we construct a novel real-time object detection framework, called RDFNet, for foggy images. Extensive experiments demonstrate that RDFNet outperforms SOTA detection methods for foggy scenes while enjoying less complexity and faster detection speeds. The source code will be released at https://github.com/PolarisFTL/RDFNet.

Object detection methods using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with adverse weather due to a lack of visibility . To tackle this problem, we propose a Multi-scale Adaptive Sampling Fusion Network, named MASFNet. In this paper, we design a Feature Adaptive Enhancement Network (FAENet) consisting of three modules to adaptively perform feature enhancement on feature maps in adverse scenarios. These modules in FAENet are integrated by the Laplace pyramid, which can perform receptive field fusion, attention perception, and affine transformation for image feature enhancement. To improve the detection performance, we propose a Multi-scale Sampling Fusion Pyramid Network (MSFNet), which is capable of fusing different scale features to improve the semantic information. Experimental results demonstrate that MASFNet achieves 73.68% and 30.95% mAP on the real scene fog dataset (RTTS) and foggy driving dataset (FDD) respectively. Additionally, on the real-world scenario low illumination dataset (ExDark), MASFNet attains a substantial mAP of 63.80%, surpassing current state-of-the-art object detectors while retaining lightweight and high-speed. The source code will be released at https://github.com/PolarisFTL/MASFNet.

Most existing super-resolution (SR) methods assume that the degradation is fixed (e.g., bicubic downsampling), whereas their performance would be degraded if the actual degradation differs from this assumption. To deal with unknown degradations, existing unknown SR methods are committed to learning degradation representation to generate high-resolution images. Nevertheless, they ignore that the impact of degradations on images is related to image content, or they learn degradation representations without any constraints. In this article, we propose a degradation maps extractor for unknown SR. Specifically, we learn degradation maps and condense them into a one-dimensional representation space to distinguish various degradations, which obtains distinguishable degradation maps and preserves the connection with the image contents. Furthermore, we propose a degradation map-guided SR (DMGSR) network, in which the degradation maps adaptively influence the SR process by applying channel attention and spatial attention to middle features. With the cooperation of the degradation maps extractor and the degradation maps-guided SR network, our network can flexibly handle various degradations. Experimental results show that our model achieves state-of-the-art performance in quantitative and qualitative metrics for the unknown SR task.

In partial label learning, each training sample corresponds to a set of candidate labels. The ground-truth label, hidden within this set, cannot be directly obtained during the training phase. The key to solving the partial label learning problem is to obtain ground-truth labels through label disambiguation. Existing works often rely on the label averaging assumption and do not fully investigate the class imbalance. Tail ground-truth labels are often overwhelmed by head pseudo-labels. The incorrectly identified labels could have contagiously negative impacts on the final predictions. In this paper, we propose a cost-guided retraining strategy, which achieves guidance and correction of disambiguation results, and provides instance-based class imbalance concerns for candidate labels. This approach significantly enhances the algorithm’s ability to handle class imbalance problems. The superiority of our method is demonstrated using 8 real-world datasets and 5 evaluation metrics. Code is available at https://github.com/DerrickZzyR/PL-CGR

Images captured under low-light conditions suffer from inevitable degradation leading to the missing global structure and detailed local texture. However, existing methods consider these two components as a single entity or perform a similar convolutional operation, which can yield suboptimal results. In this letter, we propose a dual-branch structure-texture awareness feature interaction network named DFINet to tackle the above problems. First, we generate structure and texture components through the Gaussian operator. Subsequently, we conduct CNN-based and Transformer-based branches to cope with the texture and structure components separately. Among them, we design a Feature Interaction Block that leverages local-global information to enrich features in the encoding phase. Then, we generate queries with the potential structural-texture cues for the Transformer blocks in the decoding phase. Finally, we develop a Fusion Block to progressively integrate cross-layer features from two branches for the reconstruction. Our extensive experiment indicates the proposed method outperforms several representative methods in terms of both visual quality and objective assessment.

Abstract Lowlight images with low brightness and contrast, blurry details usually bring us an uncomfortable visual experience. To promote the quality of these deviation images, this paper presents a new and efficient approach, named MFMR, for enhancing lowlight images in the hue‐saturation‐value (HSV) colour space. Concretely, the multi‐angle filter is first applied to estimate the artifact‐free illumination and reflection component of the V‐channel. Afterward, the adaptive bi‐interval histogram with human visual characteristics and morphological operations is employed to process the former, adaptive gamma correction to process the latter for generating various feature maps. In the end, these feature maps are united via adaptive multi‐scale fusion strategy to reconstruct high‐quality images, which are characterized by high contrast and brightness, vivid colour, and clearer details. Extensive experiments show that this method is a well‐proven low‐light image enhancement approach, which outperforms the state‐of‐the‐art comparison methods. Furthermore, the proposed method also can yield satisfying images in the heavy foggy, yellow sand, underwater, and other severe conditions.