Recent weakly supervised image dehazing (WSID) works have succeeded to improve models’ generalization ability to real scene dehazing by using generative adversarial network (GAN) for unpaired image training. However, it is still difficult for current WSID methods to train one effective dehazing model for various scenes since 1) they always result in residual haze due to insufficient generalization to the feature distribution of real scenes, and 2) they are prone to cause distortions like color shifts, artifacts or halos etc, owing to embedding manual prior or threshold hypothesis for image reconstruction. To solve above problems, in this paper, we propose a novel WSID model via physics-based decomposition (PBD), which estimates atmospheric light, scattering coefficient and scene depth of real haze input to effectively capture the illumination information and haze distribution to recover a preliminary dehazed image by minimizing reconstruction loss. With this constraint, we subtly design a discrete wavelet discriminator (DWD) to effectively improve the generalization to real scene from both spatial and frequency aspect under the supervision of unpaired real clear image. Our PBD is a purely data-driven model freeing from any manual setting or partially correct prior, thus simultaneously ensuring the realness and visibility of dehazed images. Experiments on seven benchmarks verified the strong generalization ability of our PBD, which achieves SOTA dehazing performance with realistic details. Code will be published at https://github.com/NianWang-HJJGCDX/PBD.

Unpaired training has been verified as one of the most effective paradigms for real scene dehazing by learning from unpaired real-world hazy and clear images. Although numerous studies have been proposed, current methods demonstrate limited generalization for various real scenes due to limited feature representation and insufficient use of real-world prior. Inspired by the strong generative capabilities of diffusion models in producing both hazy and clear images, we exploit diffusion prior for real-world image dehazing, and propose an unpaired framework named Diff-Dehazer. Specifically, we leverage diffusion prior as bijective mapping learners within the CycleGAN, a classic unpaired learning framework. Considering that physical priors contain pivotal statistics information of real-world data, we further excavate real-world knowledge by integrating physical priors into our framework. Furthermore, we introduce a new perspective for adequately leveraging the representation ability of diffusion models by removing degradation in image and text modalities, so as to improve the dehazing effect. Extensive experiments on multiple real-world datasets demonstrate the superior performance of our method.

Recent advancements in unpaired dehazing, particularly those using GANs, show promising performance in processing real-world hazy images. However, these methods tend to face limitations due to the generator's limited transport mapping capability, which hinders the full exploitation of their effectiveness in unpaired training paradigms. To address these challenges, we propose DehazeSB, a novel unpaired dehazing framework based on the Schrödinger Bridge. By leveraging optimal transport (OT) theory, DehazeSB directly bridges the distributions between hazy and clear images. This enables optimal transport mappings from hazy to clear images in fewer steps, thereby generating high-quality results. To ensure the consistency of structural information and details in the restored images, we introduce detail-preserving regularization, which enforces pixel-level alignment between hazy inputs and dehazed outputs. Furthermore, we propose a novel prompt learning to leverage pre-trained CLIP models in distinguishing hazy images and clear ones, by learning a haze-aware vision-language alignment. Extensive experiments on multiple real-world datasets demonstrate our method's superiority. Code: https://github.com/ywxjm/DehazeSB.

ABSTRACT To address the issue of recovery imbalance caused by the spatial heterogeneity of haze concentration in real scenarios, this paper proposes an adaptive feature enhanced contrastive learning framework (AFE‐Dehaze). The framework achieves breakthroughs through three major collaborative mechanisms: (1) a hierarchical multi‐scale fusion architecture that combines diffusion convolution and channel attention, preserving edge textures (such as leaf veins and building contours) in thin haze areas, while semantically guiding the reconstruction of structural details in dense haze areas, improving texture retention by 18% compared to traditional U‐Net; (2) a concentration‐sensitive contrastive learning paradigm that uses pre‐trained VGG features as semantic anchors, applying pixel‐level constraints in thin haze and feature space constraints in dense haze, which reduces color distortion () by 23%, significantly outperforming methods like refusion; (3) a gradient dynamic balancing strategy that automatically adjusts the optimization direction by analyzing positive and negative sample gradient contributions, enhancing PSNR by 1.2dB and SSIM by 0.05 in non‐uniform haze scenarios. Experiments on a mixed dataset (RESIDE OTS real scenes) demonstrate that AFE‐Dehaze achieves an average PSNR of 28.7dB and SSIM of 0.91, especially improving structural similarity in dense haze areas by 9% compared to Mamba, validating its generalization capability in complex haze environments. This framework provides a solution that balances accuracy and robustness for dehazing in real scenarios such as vehicular vision and remote sensing imaging.

Object tracking is a basic task of the uncrewed aerial vehicle (UAV)-based intelligent visual perception system. The presence of similar targets and complex backgrounds in the airborne perspective poses significant challenges to aerial trackers. However, existing target-aware or distractor-aware trackers fail to capture discriminative cues from both target and background information in a balanced manner, resulting in limited improvement. To address these issues, this paper proposes a global agent-based Target-Distractor Aware Tracker (TDAT) to enhance the discrimination of the target. TDAT comprises two effective modules: a global agent generator and an interactor. First, the generator aggregates the target and background regions into representative agents and then performs self-attention on these agents to explicitly model the global relationships between the target and backgrounds. Next, the interactor realizes the bidirectional information interaction between global agents and local regions via self-attention. Based on the global dependencies encoded in global agents, the interactor extracts target-oriented features and enhances the understanding of the target. TDAT embedded with target-distractor awareness effectively widens the gap between target and background distractors. Experimental results on multiple UAV benchmarks show that TDAT achieves outstanding performance with a speed of 34.5 frames/s. The code is available at https://github.com/xyl-507/TDAT

Image dehazing is essential to boost the visual quality of images captured in hazy conditions. Recently, many learning-based methods were proposed to achieve single image dehazing with the training of tremendous paired synthetic hazy/ real clean images. Due to the domain gap between real and synthetic scenes, these models cannot generalize well to various real hazy scenes, leading to under-dehazed results. To overcome this problem, we propose a real scene image Dehazing Network with Multi-prior Guidance and Domain Transfer (DNMGDT). Our DNMGDT is based on a parameter shared architecture trained by synthetic hazy images and real hazy images simultaneously. For real hazy images, multiple prior-based dehazed images are adopted as pseudo clean images. An Image Quality Guided Adaptive Weighting (IQGAW) scheme is proposed to form the supervision by automatically weighting different parts of these prior-based dehazed images and suppressing negative information of them. Moreover, to reduce the domain gap between real and synthetic hazy scenes, a Physical Model Guided image level Domain Transfer (PMGDT) mechanism is proposed to regularize the learning process with consistency constraint. Experiments on various datasets demonstrated the effectiveness of our proposed method especially for real hazy scenes.

Graph-based clustering is a hot topic in machine learning, whose effectiveness highly relies on the quality of the learned graph. Recent researches preferred to learn the nearest doubly stochastic approximation of a graph to suppress intercluster connections and enhance intracluster connections and thus improve clustering performance. While current paradigm is limited by three key problems: 1) it is restricted by a predefined graph; 2) the separated stages of spectral decomposition-based way (graph learning, spectral embedding learning, and cluster assignment by k-means) cause mismatched problems and randomness; and 3) the optimization of doubly stochastic conditions is generally achieved by von Neumann successive projection (VNSP) lemma, which separates the conditions to form two subproblems for alternative optimization, converging only to a feasible solution. To solve these problems, in this article, a novel structured doubly stochastic graph-based clustering model termed SDSGC is proposed, which learns a structured doubly stochastic graph from data to directly provide cluster indicators. For optimization, a simple but effective augmented Lagrangian multiplier (ALM)-based method is proposed, which optimizes all the doubly stochastic conditions simultaneously to obtain the optimal solution. Experiments on one toy dataset and eight ad hoc noised face datasets have demonstrated that the proposed SDSGC is more robust to noise. Furthermore, a quantitative comparison of ten benchmarks has verified our SDSGC achieves better clustering performance when compared with SOTA methods. The code is available at https://github.com/NianWang-HJJGCDX/SDSGC.git.

Aerial tracking has received growing attention due to its broad practical applications. However, single-view aerial trackers are still limited by challenges such as severe appearance variations and occlusions. Existing multi-view trackers utilize cross-drone information to address these issues but struggle to overcome heterogenous differences. In this paper, we propose a novel Transformer-based consistent representation mining (CRM) module to capture invariant target information and suppress the heterogenous differences in cross-drone information. First, CRM divides the heterogenous input into regions and measures semantic relevance by modeling the relations between these regions. Then reliable target regions are roughly localized by selecting the top k most relevant regions. Next, the global perception is performed on these reliable regions via multi-head sparse self-attention, further enhancing the understanding of the target and suppressing background regions. In particular, CRM, as a plug-and-play module, can be flexibly embedded into different tracking frameworks (CRM-Siam and CRM-DiMP). Besides, the multi-view correction strategy is designed to ensure timely correction of multi-view information and full utilization of its own information. Extensive experiments on the multi-drone dataset, MDOT, demonstrate that CRM-assisted trackers effectively improve the accuracy and robustness of the multi-drone tracking system, outperforming other outstanding trackers. The code and models are available athttps://github.com/xyl-507/CRM.

Aerial object tracking has recently shown great potential in the field of remote sensing. However, small objects with limited feature information pose a huge challenge to aerial trackers. Despite significant improvements, most trackers still struggle to capture enough discriminative features and to overcome background disturbances. In this work, we propose an efficient aerial tracker (SmallTrack) based on the Siamese network to improve the discrimination of small objects. It consists of two effective modules, namely Wavelet Pooling Layer (WPL) and Graph Enhanced Module (GEM). First, WPL decomposes the input into four subbands via wavelet domain learning, and fully utilizes the high- and low-frequency information in the subbands to preserve the discriminative features of small objects. Second, GEM embeds the pixels on the classification responses as nodes in graph learning through graph neural networks, which naturally mines the similarity between pixels. Based on the pixel-level modulation constructed from graph theory, GEM enhances the understanding of small objects and highlights them in the classification responses. The proposed tracker achieves leading performance on five aerial benchmarks, while maintaining a high running speed of 72.5 frames/s. Besides, real-world tests on an aerial platform have proven the effectiveness of SmallTrack. The code and models are available at https://github.com/xyl-507/SmallTrack.

End-to-end learning-based image dehazing methods tend to overdehaze or underdehaze in real scenes due to inefficient feature extraction and feature fusion. In this letter, we propose a multiscale supervision-guided context aggregation network (MSGCAN) based on two principles: improving feature extraction and enhancing feature mapping. To improve feature extraction, an attention-guided context aggregation (AGCA) module is adopted to merge context features extracted by several residual dense blocks (RDB). Moreover, we output these aggregated context features on each scale and form multiscale supervision to enhance feature mapping and ensure that the extracted features on each scale contain more realistic details. The experimental results show that the proposed MSGCAN performs better than other state-of-the-art dehazing methods in both synthetic and real-world scenes.

Abstract Single‐image dehazing is an important problem because it is a key prerequisite for most high‐level computer vision tasks. Traditional prior‐based methods adopt priors generated from clear images to restrain the atmospheric scattering model and then recover haze‐free images. However, these prior‐based methods always encounter over‐enhancement, such as halos and colour distortion. To solve this problem, many works use a convolutional neural network to retrieve original images. However, without priors as guidance, these learning‐based methods dehaze effectively in synthetic datasets but perform poorly in real scenes. Hence, in this paper, we propose a prior‐guided multiscale network for single‐image dehazing named PGMNet. Specifically, prior‐based methods are adopted to acquire dehazed images of the training dataset in advance and then send these dehazed images to a parameter‐shared encoder to form multiscale features. During the decoding process, these multiscale features are adopted to guide the prior‐guided multiscale network to recover more image details. Moreover, considering that these prior‐based dehazed images usually contain some over‐enhanced regions, a spatial attention guided feature aggregation module and squeeze‐and‐excitation module are adopted to alleviate colour distortion. The proposed PGMNet takes the advantage of prior‐based methods in real haze removal and provides superior performance compared with the state‐of‐the‐art methods on both synthetic and real‐world datasets.