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.

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. The official codes see https://github.com/NianWang-HJJGCDX/DNMGDT

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 at https://github.com/xyl-507/CRM.

Aerial tracking has recently shown significant potential in vision-based measurement. Despite significant improvements, accurate occlusion tracking remains a difficult challenge. Existing training enhancement or global search struggles to handle occlusion in aerial views due to similar distractors and background interferences. To handle occlusion in aerial tracking, we propose a query-guided redetection tracker (QRDT) based on a Siamese neural network, improving the redetection discrimination from three stages. First, the query update branch is introduced to keep the target appearance dynamically updated via inter-frame information transfer. Next, we propose the cross fusion layer, which models the semantic correlation between the search feature and updated query feature, to draw attention to the occluded target. Finally, to address tracking failure and distraction from similar targets, the trajectory during full occlusion is reliably predicted by the Kalman filter. Our tracker achieves leading tracking performance on several benchmarks, with an average speed of 48.9 frames/s. The code and models are available at https://github.com/xyl-507/QRDT.

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.