Synthetic aperture radar (SAR) images are often affected by a type of multiplicative noise known as “speckle” due to their active imaging characteristics.This property complicates the processing and interpretation of SAR images. While deep learning techniques have demonstrated success in despeckling many models are tailored to specific noise levels. This specificity can limit a model's ability to generalize to real SAR images with varying noise levels, potentially leading to over-smoothing or over-focusing on specific details. To address these challenges, we present the Adaptive Noise Estimation and Despeckling Network (ANED-Net). This network consists of a noise-level estimation phase and a noise-level-guided non-blind denoising phase. During the non-blind denoising phase, we develop a Noise Feature-Guided Denoising Network (NFGDN). This network integrates a hierarchical encoder-decoder denoising module based on the Transformer block (T-unet) and a Denoising Enhancement Control (DEC) block. Together, they skillfully capture both local and global dependencies inherent in SAR images, facilitating effective noise removal. Furthermore, we also introduce a Deep-attention mechanism to counteract the attentional collapse observed when the Transformer is extended in depth, enhancing the network's feature extraction capability and strengthening the model's denoising performance. Extensive tests on synthetic and real images show that ANED-Net is robust to different noise scenarios. It effectively mitigates speckle noise even at unspecified levels, and outperforms many established methods.

Oriented remote sensing object detection (ORSOD) has gained increasing significance in both military and civilian applications due to the necessity of accurately identifying objects with varying shapes and orientations in remote sensing data. Traditional ORSOD methods often employ fixed label assignment strategies to differentiate between positive and negative samples. However, most of them frequently overlook the impact of object shape on sample quality, leading to an imbalanced distribution of positive samples and exacerbating the inconsistency between classification and regression tasks, thereby limiting detection performance. To address these challenges, we propose a novel shape-dependent assignment (SDA) method that dynamically differentiates positive and negative samples based on object shape. It introduces a new metric for evaluating sample box quality by considering angular differences relative to ground truth (GT) boxes and adjusts the sample scoring threshold according to the aspect ratio of each GT box. In addition, we present a DIoU-adaptive weighting (DAW) module that enhances the interaction between classification and regression tasks by leveraging the distance-IoU metric. This approach not only balances the quantity of samples but also improves their quality, enabling more effective training schemes for samples of varying qualities. We validate our proposed methods through extensive experiments on three challenging ORSOD datasets: DOTA-1.0, HRSC2016, and UCAS-AOD. The results demonstrate that our approach achieves significant improvements, especially for objects with large aspect ratios.

Oriented remote sensing object detection (ORSOD) remains challenging because objects usually appear at arbitrary rotations, with large aspect-ratio variations and dense spatial layouts. Although recent detectors have achieved notable progress, most still rely on standard convolutional backbones, whose limited inherent rotation equivariance weakens robustness to rotated targets and reduces localization reliability. To address these issues, this paper proposes RedhDet, an ORSOD framework based on rotation-equivariant feature learning and dual-head decoupling. Specifically, a Ladder-Structured Implicitly Equivariant Network (LSIEN) is developed as the backbone to extract rotation-equivariant features in a soft manner, without relying on strictly constrained kernels or equivariant pre-trained weights. In addition, a decoupled dual-head architecture is introduced, in which a fully connected branch is used for classification and a convolutional branch is used for bounding box regression, thereby better matching the distinct requirements of semantic recognition and precise localization. Experimental results on the DOTA-1.0 and HRSC2016 datasets demonstrate the effectiveness of the proposed method. On the DOTA-1.0 test set, RedhDet improves mAP₅₀ by 2.09% and mAP₇₅ by 14.84% over the baseline. On HRSC2016, gains of 14.12% and 51.85% are achieved for mAP₅₀ and mAP₇₅, respectively. With multi-scale training and testing, the proposed method achieves 80.40% mAP on DOTA-1.0, indicating its effectiveness and competitiveness for ORSOD.

Oriented object detection is essential for interpreting high-resolution remote-sensing images, but detectors trained on a single source domain often suffer from severe performance degradation under unseen imaging conditions. Existing domain generalization methods mainly address horizontal detection or treat style variation as an undifferentiated perturbation, while the geometry-sensitive nature of oriented objects, especially elongated instances, is insufficiently considered. To address these limitations, a shape-adaptive learning and style-aware decomposition framework, termed SA-DGOD, is proposed for single-source domain-generalized oriented object detection. A frozen CLIP image encoder is employed only during training to provide multi-level style statistics, from which several interpretable branch-style pseudo-domains are constructed by modulating feature statistics that characterize photometric and contrast variations. These explicit pseudo-domain identities enable structured style diversification without accessing target-domain data. To improve orientation-sensitive representation learning, a shape-adaptive soft consistency loss is introduced for rotated RoI features. Instead of using a fixed-threshold binary weighting scheme, the proposed loss adopts an aspect-ratio-aware threshold and a continuous rotated-IoU-based weight, allowing elongated objects and geometrically reliable proposals to be handled more flexibly. Furthermore, a style-aware common-specific classifier decomposition is introduced into the proposed framework to separate domain-invariant category discrimination from pseudo-domain-specific style bias. Extensive experiments on multiple remote sensing benchmarks demonstrate the effectiveness and generalization capability of SA-DGOD.