Object detection is a core task in computer vision, yet its performance is severely degraded in low-light environments, where foreground objects blend into the background, feature contrast is reduced, and object boundaries become blurred, ultimately impairing detection accuracy. To address this problem, we propose FFE-DETR, an end-to-end detection framework specifically designed for low-light scenes. The model incorporates a Frequency-Aware Feature Enhancer that applies Laplacian pyramid decomposition to separate low-frequency and high-frequency components. The low-frequency features are globally modeled to enhance foreground saliency and emphasize object boundaries, and the enhanced representation subsequently guides high-frequency detail restoration and noise suppression, yielding clearer and more discriminative features. In addition, a Multi-Scale Adaptive Feature Fusion module is introduced to efficiently integrate shallow texture information with deep semantic cues, enhancing the feature representation capability across different scales. Experimental results on widely used low-light benchmarks demonstrate that FFE-DETR consistently outperforms state-of-the-art methods and achieves significantly superior detection accuracy, highlighting its effectiveness and robustness.

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.

Despite the superiority of convolutional neural networks (CNNs) and Transformers in single-image rain removal, current multi-scale models still face significant challenges due to their reliance on single-scale feature pyramid patterns. In this paper, we propose an effective rain removal method, the dual-path multi-scale Transformer (DPMformer) for high-quality image reconstruction by leveraging rich multi-scale information. This method consists of a backbone path and two branch paths from two different multi-scale approaches. Specifically, one path adopts the coarse-to-fine strategy, progressively downsampling the image to 1/2 and 1/4 scales, which helps capture fine-scale potential rain information fusion. Simultaneously, we employ the multi-patch stacked model (non-overlapping blocks of size 2 and 4) to enrich the feature information of the deep network in the other path. To learn a richer blend of features, the backbone path fully utilizes the multi-scale information to achieve high-quality rain removal image reconstruction. Extensive experiments on benchmark datasets demonstrate that our model reaches superior performance, significantly improving the image deraining quality.

Recently, Transformer-based methods have achieved significant improvements over convolutional neural networks (CNNs) in single image deraining, due to the powerful ability of modeling non-local information. In fact, rich local-global information representations are equally important for better satisfying rain removal. In this paper, we propose an effective image deraining method by integrating a CNN model into the Transformer backbone to accelerate network convergence, called Multi-scale Dilated-convolution Transformer (MDT), which fully leverages the learning capabilities of Transformers on non-local features, seamlessly integrating local detail extraction and global structural representation. The fundamental building unit of our framework is the Multi-scale Dilated-convolution Transformer Block (MDTB) with different dilation rates, which consists of the Dilconv Self-Attention (DSA) and the Dilconv Feed-Forward Network (DFN). Specifically, the former processes the contextual information via dilated convolutions and enables the model to emphasize spatially-varying rain distribution features, while the latter integrates the dual-branch information to facilitate the local feature learning for better feature aggregation. Extensive evaluations demonstrate that our model reaches superior performance, significantly improving the image deraining quality.

Learning single image deraining (SID) networks from an unpaired set of clean and rainy images is practical and valuable as acquiring paired real-world data is almost infeasible. However, without the paired data as the supervision, learning a SID network is challenging. Moreover, simply using existing unpaired learning methods (e.g., unpaired adversarial learning and cycle-consistency constraints) in the SID task is insufficient to learn the underlying relationship from rainy inputs to clean outputs as there exists significant domain gap between the rainy and clean images. In this paper, we develop an effective unpaired SID adversarial framework which explores mutual properties of the unpaired exemplars by a dual contrastive learning manner in a deep feature space, named as DCD-GAN. The proposed method mainly consists of two cooperative branches: Bidirectional Translation Branch (BTB) and Contrastive Guidance Branch (CGB). Specifically, BTB exploits full advantage of the circulatory architecture of adversarial consistency to generate abundant exemplar pairs and excavates latent feature distributions between two domains by equipping it with bidirectional mapping. Simultaneously, CGB implicitly constrains the embeddings of different exemplars in the deep feature space by encouraging the similar feature distributions closer while pushing the dissimilar further away, in order to better facilitate rain removal and help image restoration. Extensive experiments demonstrate that our method performs favorably against existing unpaired deraining approaches on both synthetic and real-world datasets, and generates comparable results against several fully-supervised or semi-supervised models.

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 H2RL-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, H2RL-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.

As a fundamental vision-based task in the remote sensing filed, object detection has achieved significant progress. However, remote sensing object detection is still an urgent challenge owing to dense distribution, large aspect ratio, and arbitrary orientations. To address this issue, we develop an end-to-end dual align single-stage rotation detector (DA-Net) consisting of two main components: a Rotation Feature Selection (RFS) module and a Rotation Feature Align (RFA) module. Specifically, RFS module can empower neurons with the capability to adjust receptive fields, which achieves the first stage of feature alignment on the image level. Furthermore, RFA module is employed to adaptively align the feature based on the size, shapes, orientations of its corresponding anchors, realizing the second stage of instance-level feature alignment. Extensive experiments have shown that our DA-Net can significantly improve remote sensing detection performance against several start-of-the-art algorithms on two benchmark datasets.

Most existing single image dehazing methods aim to learn supervised models from paired synthetic data, which often limits their generalization ability in real-world applications. Besides, due to ignoring the merits of physical model in visibility restoration and the properties of depth features in clarity improvement, we observe that only relying on the transfer capability of unpaired adversarial learning will suffer from low-quality recovery. To this end, we develop an effective end-to-end unpaired image dehazing method by integrating a physical-guided restoration stage and a depth-guided refinement stage in a GAN framework, named as PDR-GAN. Specifically, the dark channel prior is embedded in the restoration stage to provide constraints for the network, and the preliminary dehazed image is first generated. For the refinement stage, we excavate the potential relationship between the depth and transmission map to better refine the results of the previous stage and further recover the distant area details. Our framework benefits from the stage-wise learning strategy of model-based restoration and feature-based reconstruction, which is especially helpful for image dehazing when paired data is not available. Experimental results show that our method is superior to the current unpaired dehazing approaches in terms of both quantitative and qualitative.

Recently, deep learning based models have been extensively applied to image restoration and enhancement tasks. However, existing approaches neglect the potential correlation among these tasks, and do not fully consider the different intensity factors of degradation which affect image quality. To this end, we propose Task-Adaptive Operation Network (TAO-Net) that stacks a series of operation blocks, guided by the supervised attention mechanism to adaptively enable the model to assign corresponding intensity weights for different degradation factors depending on the input signals. To better recover and preserve the accurate details during the repeated operations, we make full use of the image prior to intruduce structure refinement block as auxiliary information for reconstructing high-quality results. Furthermore, feature aggregation block is also adopted to avoid feature interference caused by the direct concatenation between the backbone operation block and the auxiliary refinement block together. Extensive experiments on multiple benchmark datasets demonstrate that our proposed method outperforms previous baselines in image deraining and low-light image enhancement.

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 athttps://github.com/cxtalk/FCTF-Net.

In order to improve the H.264/AVC compressed video stream error resilience in wireless channel transmission, this paper presents a spatial error concealment algorithm based on adaptive edge threshold and directional weight. Firstly, this algorithm makes use of Sobel gradient operator of image edge detection to detect the edge of adjacent macro blocks; secondly, according to specific information of adjacent macro-block of damaged macro-block, it can set gradient adaptive threshold; thirdly, it makes the direction weighted interpolation to damaged macro-block with the Sobel gradient operator of image edge detection. Experiments show that the image reconstruction quality is greatly improved by using this algorithm, which has higher application value for different video sequence as compared to the traditional spatial error concealment algorithms. This algorithm not only improves the quality of image restoration, but also has higher application value.