In many remote sensing (RS) applications, haze seriously degrades the quality of optical RS images and even brings inconvenience to the following high-level visual tasks such as RS detection. In this letter, we address this challenge by designing a first-coarse-then-fine two-stage dehazing neural network, named FCTF-Net. The structure is simple but effective: the first stage of image dehazing extracts multiscale features through the encoder-decoder architecture and, therefore, allows the second stage of dehazing for better refining the results of the previous stage. In addition, we combine the channel attention mechanism with the basic convolution block, considering that different channel characteristics contain entirely different weighting information, to effectively deal with irregular distribution of haze in RS images. Owing to the scarcity of various and quality hazy RS data sets, we adopt two different synthesis methods to generate large-scale image pairs for uniform and nonuniform hazy images. This two-stage network, when trained in an end-to-end fashion, yields the state-of-the-art performances on both the synthetic data sets and real-world images with more visually pleasing dehazed results. Both the synthetic data set and the code are publicly available at https://github.com/cxtalk/FCTF-Net.

Since rain streaks exhibit diverse geometric appearances and irregular overlapped phenomena, these complex characteristics challenge the design of an effective single image deraining model. To this end, rich local-global information representations are increasingly indispensable for better satisfying rain removal. In this paper, we propose a lightweight Hybrid CNN-Transformer Feature Fusion Network (dubbed as HCT-FFN) in a stage-by-stage progressive manner, which can harmonize these two architectures to help image restoration by leveraging their individual learning strengths. Specifically, we stack a sequence of the degradation-aware mixture of experts (DaMoE) modules in the CNN-based stage, where appropriate local experts adaptively enable the model to emphasize spatially-varying rain distribution features. As for the Transformer-based stage, a background-aware vision Transformer (BaViT) module is employed to complement spatially-long feature dependencies of images, so as to achieve global texture recovery while preserving the required structure. Considering the indeterminate knowledge discrepancy among CNN features and Transformer features, we introduce an interactive fusion branch at adjacent stages to further facilitate the reconstruction of high-quality deraining results. Extensive evaluations show the effectiveness and extensibility of our developed HCT-FFN. The source code is available at https://github.com/cschenxiang/HCT-FFN.

Recent years have witnessed significant advances in image deraining due to the progress of effective image priors and deep learning models. As each deraining approach has individual settings (e.g., training and test datasets, evaluation criteria), how to fairly evaluate existing approaches comprehensively is not a trivial task. Although existing surveys aim to thoroughly review image deraining approaches, few of them focus on unifying evaluation settings to examine the deraining capability and practicality evaluation. In this paper, we provide a comprehensive review of existing image deraining methods and provide a unified evaluation setting to evaluate their performance. Furthermore, we construct a new high-quality benchmark named HQ-RAIN to conduct extensive evaluations, consisting of 5,000 paired high-resolution synthetic images with high harmony and realism. We also discuss existing challenges and highlight several future research opportunities worth exploring. To facilitate the reproduction and tracking of the latest deraining technologies for general users, we build an online platform to provide the off-the-shelf toolkit, involving the large-scale performance evaluation.

Existing Transformer-based image deraining methods depend mostly on fixed single-input single-output U-Net architecture. In fact, this not only neglects the potentially explicit information from multiple image scales, but also lacks the capability of exploring the complementary implicit information across different scales. In this work, we rethink the multi-scale representations and design an effective multi-input multi-output framework that constructs intra- and inter-scale hierarchical modulation to better facilitate rain removal and help image restoration. We observe that rain levels reduce dramatically in coarser image scales, thus proposing to restore rain-free results from the coarsest scale to the finest scale in image pyramid inputs, which also alleviates the difficulty of model learning. Specifically, we integrate a sparsity-compensated Transformer block and a frequency-enhanced convolutional block into a coupled representation module, in order to jointly learn the intra-scale content-aware features. To facilitate representations learned at different scales to communicate with each other, we leverage a gated fusion module to adaptively aggregate the inter-scale spatial-aware features, which are rich in correlated information of rain appearances, leading to high-quality results. Extensive experiments demonstrate that our model achieves consistent gains on five benchmarks.

Recently, deep learning models have shown convincing performance in removing a single satellite image haze, which arouses increasing attention in the field of remote sensing (RS). Unfortunately, these models still suffer from an insufficient ability to recover the desired fine spatial details from the hazy image. In this letter, we first attempt to explore an end-to-end hybrid high-resolution learning network framework termed H ² RL-Net to address this issue due to its novel feature extraction architecture, where spatially precise outputs are guaranteed by the main high-resolution branch and semantically richer features are collected by the complementary set of multiresolution convolution streams. To improve representation learning, H ² RL-Net is constructed primarily by exploiting the parallel cross-scale fusion (PCF) module, thereby increasingly aggregating information from the multiple scales at the respective resolution level, which allows both top-down and bottom-up information exchanging processes. Simultaneously, we also introduce the channel feature refinement (CFR) block to our model, aiming to perform dynamic feature recalibration among the channelwise features and produce better dehazed results. The experimental analysis illustrates that the designed framework can deliver significant improvements over other baseline methods in the synthetic and real-world hazy RS images under various scenes.

Convolutional neural networks (CNNs) and Transformers have achieved significant success in image signal processing. However, little effort has been made to effectively combine the properties of these two architectures to satisfy image deraining. In this paper, we propose an effective de-raining method, dilated convolutional Transformer (DCT), which can enlarge the receptive fields of the network to aggregate global information. The fundamental building unit of our approach is the dilformer block containing multi-dilconv sparse attention (MDSA) and multi-dilconv feed-forward network (MDFN). The MDSA calculates the multi-scale query to generate accurate similarity map so that rich multi-scale information can be better utilized for the high-quality image reconstruction. In addition, we adopt ReLU to replace the original softmax to enforce sparsity in the Transformer for better feature aggregation. The MDFN is further established to better integrate the rain information of different scales in the feature transformation. Extensive experiments on the benchmarks show the favorable performance against state-of-the-art approaches.