Existing all-in-one image restoration approaches, which aim to handle multiple weather degradations within a single framework, are predominantly trained and evaluated using mixed single-weather synthetic datasets. However, these datasets often differ significantly in resolution, style, and domain characteristics, leading to substantial domain gaps that hinder the development and fair evaluation of unified models. Furthermore, the lack of a large-scale, real-world all-in-one weather restoration dataset remains a critical bottleneck in advancing this field. To address these limitations, we present a real-world all-in-one adverse weather image restoration benchmark dataset, which contains image pairs captured under various weather conditions, including rain, snow, and haze, as well as diverse outdoor scenes and illumination settings. The resulting dataset provides precisely aligned degraded and clean images, enabling supervised learning and rigorous evaluation. We conduct comprehensive experiments by benchmarking a variety of task-specific, task-general, and all-in-one restoration methods on our dataset. Our dataset offers a valuable foundation for advancing robust and practical all-in-one image restoration in real-world scenarios. The dataset has been publicly released and is available at https://github.com/guanqiyuan/WeatherBench.

Compared to daytime image deraining, nighttime image deraining poses significant challenges due to inherent complexities of nighttime scenarios and the lack of high-quality datasets that accurately represent the coupling effect between rain and illumination. In this paper, we rethink the task of nighttime image deraining and contribute a new high-quality benchmark, HQ-NightRain, which offers higher harmony and realism compared to existing datasets. In addition, we develop an effective Color Space Transformation Network (CST-Net) for better removing complex rain from nighttime scenes. Specifically, we propose a learnable color space converter (CSC) to better facilitate rain removal in the Y channel, as nighttime rain is more pronounced in the Y channel compared to the RGB color space. To capture illumination information for guiding nighttime deraining, implicit illumination guidance is introduced enabling the learned features to improve the model's robustness in complex scenarios. Extensive experiments show the value of our dataset and the effectiveness of our method. The source code and datasets are available at https://github.com/guanqiyuan/CST-Net.

Transformer-based methods have gradually shown excellent performance in remote sensing (RS) image dehazing tasks. The self-attention can effectively explore nonlocal features, which are crucial for restoring images obscured by haze. However, when the tokens from the query differ from those of the key, these low-correlation self-attention values will still be included in the calculations indiscriminately, leading to further interference in the reconstruction of clear images. To better aggregate features, we propose a prompt-guided sparse Transformer (PGSformer). Specifically, adaptive top-k guided attention (ATGA) utilizes the top-k selection operator (TSO) to preserve the most important attention scores from the keys for each query, preventing interference from low-correlation query-key pairs in self-attention calculation. Meanwhile, we design the learnable prompt block (LPB) within ATGA to further enhance the accuracy of sparse selection for attention enhancement. Here, LPB guides the TSO dynamically optimizing sparse rate and adaptively learning mask thresholds to further distill the selected features. In addition, the frequency selection feedforward network (FSFN) is designed to adaptively obtain frequency information, so that the overall pipeline can improve the learning ability of dual frequency features. Extensive experimental results on several benchmarks show that our PGSformer outperforms the other competitive dehazing approach (RSDformer) by 0.92 dB on average PSNR.

In the field of remote sensing, cloud and cloud shadow detection (CCSD) presents a challenging task aimed at identifying inevitable clouds and cloud shadows (CCSs) within remote sensing images. Existing studies have tried to enhance detection performance through the design of intricate large-scale networks. These methods have obtained significant performance gains. However their high memory and computational overhead limit their applicability. Hence, in this letter, we propose a lightweight prior-knowledge guided transformer (LPGT). First, prior information from CCS is captured in prior-knowledge extraction (PKE), guiding the model to focus on the spatial relationships of CCS within the context, thereby further refining long-range dependencies. Next, a prior-guided efficient attention block (PEAB) is introduced as the fundamental feature extraction unit of LPGT, which contains depth-wise convolutions and expanded window multihead self-attention (SA) to enhance the computation capability of the model and reduces the intensive computational burden. Finally, a feature refinement block (FRB) is developed to improve the model’s local feature extraction capabilities for comprehensively understanding the contextual image maps, enabling accurate distinguishing between CCS. Extensive experimental results on the GF-1 wide field-of-view (WFV) dataset indicate that the proposed method achieves more competitive mean intersection over union (mIoU) performance while having fewer parameters and FLOPs.

In recent years, Transformer has witnessed significant progress in the single image deraining field. However, most existing methods do not consider the latent sparse representation and distinguished frequency information. To this end, this paper proposes an effective Image Deraining Transformer with Sparsity and Frequency Guidance, called SFG-IDT. To achieve such guidance, the proposed method consists two key designs: sparsity-compensated multi-head attention (SCMA) and frequency-enhanced multi-scale operator (FEMO). Specifically, the SCMA enhances the concentration of attention while explicitly retaining non-local connectivity with Locality Sensitive Hashing (LSH), to facilitate rain removal better and help image restoration. Simultaneously, the FEMO integrates the frequency information into the multi-scale convolution operators with Fast Fourier Transform (FFT) to obtain a more accurate representation for achieving high-quality derained results. Extensive experimental results show that our developed SFG-IDT outperforms the state-of-the-art approach (Restormer) by 0.27 dB on average, but saves 50.3% parameters and 46.7% computational cost.

The existing remote sensing (RS) image dehazing methods based on deep learning have sought help from the convolutional frameworks. Nevertheless, the inherent limitations of convolution,i.e., local receptive fields and independent input elements, curtail the network from learning the long-range dependencies and non-uniform distributions. To this end, we design an effective RS image dehazing Transformer architecture, denoted as RSDformer. Firstly, given the irregular shapes and non-uniform distributions of haze in RS images, capturing both local and non-local features is crucial for RS image dehazing models. Hence, we propose a detail-compensated transposed attention to extract the global and local dependencies across channels. Secondly, to enhance the ability to learn degraded features and better guide the restoration process, we develop a dual-frequency adaptive block with dynamic filters. Finally, a dynamic gated fusion block is designed to achieve fuse and exchange features across different scales effectively. In this way, the model exhibits robust capabilities to capture dependencies from both global and local areas, resulting in improving image content recovery. Extensive experiments prove that the proposed method obtains more appealing performances against other competitive methods.