Pansharpening is a powerful technique for generating high-resolution multispectral (HRMS) images by fusing currently available image pairs of low-resolution multispectral (LRMS) and texture-rich panchromatic (PAN) data, effectively addressing the physical constraints of satellite sensors. While recent generative diffusion models have demonstrated impressive performance gains in this domain, their prohibitive computational demands and training costs hinder practicality in resource-constrained remote sensing satellite systems. In this work, we propose NODiff, a novel diffusion framework that replaces the conventional attention-based denoising backbone with a neural operator, seamlessly integrating operator learning and generative modeling into an efficient yet effective solution for pansharpening. In practice, we implement our approach through a two-stage learning paradigm: First, we pretrain the proposed Neural Operator-based diffusion model to learn the high-resolution texture priors essential for pansharpening. Afterward, we freeze the pretrained parameters, and design a lightweight conditional detail guidance adapter to enable efficient fine-tuning for generating desired HRMS images. Meanwhile, a time-aware low-rank adaptation is introduced to dynamically refine high-frequency details potentially affected by spectral mode truncation. Extensive experiments on multiple benchmark datasets demonstrate that NODiff achieves competitive pansharpening performance while significantly reducing training and inference costs. Beyond pansharpening, our method provides new insights into building resource-efficient generative models.

Image-based virtual try-on (VTON) aims to synthesize photorealistic images of a person wearing specified garments. Despite significant progress, building a universal VTON framework that can flexibly handle diverse and complex tasks remains a major challenge. Recent methods explore multi-task VTON frameworks guided by textual instructions, yet they still face two key limitations: (1) semantic gap between text instructions and reference images, and (2) data scarcity in complex scenarios. To address these challenges, we propose UniFit, a universal VTON framework driven by a Multimodal Large Language Model (MLLM). Specifically, we introduce an MLLM-Guided Semantic Alignment Module (MGSA), which integrates multimodal inputs using an MLLM and a set of learnable queries. By imposing a semantic alignment loss, MGSA captures cross-modal semantic relationships and provides coherent and explicit semantic guidance for the generative process, thereby reducing the semantic gap. Moreover, by devising a two-stage progressive training strategy with a self-synthesis pipeline, UniFit is able to learn complex tasks from limited data. Extensive experiments show that UniFit not only supports a wide range of VTON tasks, including multi-garment and model-to-model try-on, but also achieves state-of-the-art performance.

Nighttime hazy vision is severely limited by the presence of haze and multi-colored light sources. Different from the daytime image dehazing task which has been widely studied, less progress has been made in nighttime image dehazing. In this paper, through extensive analysis and experimentation, we find that game engine simulations offer strong real-world generalization but suffer from unrealistic brightness. To tackle this, we introduce a three-step, brightness-aware synthetic-to-real learning approach. First, we use supervised learning to train a spatial-frequency network (SFN) on synthetic data to produce pseudo-labels. With these pseudo-labels, we develop a semi-supervised dehazing model (SFN+) that minimizes domain discrepancy through a brightness consistency loss applied to local windows. Building on SFN+, we fine-tune the model for better vision using a relative brightness improvement strategy that accounts for color shifts from lighting and brightness shifts during enhancement (SFN++). Experiments on popular benchmark datasets confirm our method's superiority over state-of-the-art approaches.

Contrastive adversarial training emerges as an effective approach to enhancing model robustness in safety-critical applications, particularly point cloud recognition for autonomous driving and medical imaging. However, existing point cloud adversarial training methods mainly emphasize global contrastive learning while overlooking local geometric variations induced by adversarial perturbations. Motivated by the spatial and intensity variations of perturbations across axial views, we propose AVOC, a novel local-global adversarial training framework that utilizes axial-view-oriented contrastive learning. This framework leverages the smallest axial view for local contrastive learning, as it exhibits the highest perturbation differences, and utilizes the largest axial view for global contrastive learning, as it preserves global structural consistency. We conduct comprehensive experiments across four representative architectures, demonstrating significant robustness improvements on widely-adopted recognition benchmarks, including ModelNet40, ShapeNetPart, ModelNet40-C, and ScanObjectNN-C, and further validate its effectiveness on the large-scale KITTI benchmark for 3D object detection. Our results across diverse perturbation scenarios, encompassing white-box attacks, black-box attacks, and natural perturbations, demonstrate the consistent and significant model robustness enhancement of our proposed method.

Pan-sharpening technology refers to generating a high-resolution (HR) multi-spectral (MS) image with broad applications by fusing a low-resolution (LR) MS image and HR panchromatic (PAN) image. While deep learning approaches have shown impressive performance in pan-sharpening, they generally require extensive hardware with high memory and computational power, limiting their deployment on resource-constrained satellites. In this study, we investigate the use of binary neural networks (BNNs) for pan-sharpening and observe that binarization leads to distinct information degradation across different frequency components of an image. Building on this insight, we propose a novel binary pan-sharpening network, termed BNNPan, structured around the Prior-Integrated Binary Frequency (PIBF) module that features three key ingredients: Binary Wavelet Transform Convolution, Latent Diffusion Prior Compensation, and Channel-wise Distribution Calibration. Specifically, the first decomposes input features into distinct frequency components using Wavelet Transform, then applies a "divide-and-conquer" strategy to optimize binary feature learning for each component, informed by the corresponding full-precision residual statistics. The second integrates a latent diffusion prior to compensate for compromised information during binarization, while the third performs channel-wise calibration to further refine feature representation. Our BNNPan, developed with the proposed techniques, achieves promising pan-sharpening performance on multiple remote sensing datasets, surpassing state-of-the-art binarization algorithms.

Over the past decades, pansharpening has contributed greatly to numerous remote sensing applications, with methods evolving from theoretically grounded models to deep learning approaches and their hybrids. Though promising, existing methods rarely address pansharpening through the lens of underlying physical imaging processes. In this work, we revisit the spectral imaging mechanism and propose a novel physics‐informed neural operator framework for pansharpening, termed PINO, which faithfully models the end‐to‐end electro‐optical sensor process. Specifically, PINO operates as: (1) First, a spatial-spectral encoder pair is introduced to aggregate multi-granularity high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) features. (2) Subsequently, an iterative neural integral process utilizes these fused spatial-spectral characteristics to learn a continuous radiance field $L_i(x, y, \lambda)$ over spatial coordinates and wavelength, effectively emulating band-wise spectral integration. (3) Finally, the learned radiance field is modulated by the sensor’s spectral responsivity $R_b(\lambda)$ to produce physically consistent spatial–spectral fusion products. This physics-grounded fusion paradigm offers a principled solution for reconstructing high-resolution multispectral and hyperspectral images in accordance with sensor imaging physics, effectively harnessing the unique advantages of spectral data to better uncover real-world characteristics. Experiments on multiple benchmark datasets show that our method surpasses state-of-the-art fusion algorithms, achieving reduced spectral aberrations and finer spatial textures. Furthermore, extension to hyperspectral (HS) data demonstrates its generalizability and universality. The code will be available upon potential acceptance.

Pan-sharpening essentially to boost the spatial resolution of a multispectral (MS) image guided by its paired panchromatic (PAN) image. In other words, this process intricately integrates the high-frequency components extracted from texture-rich PAN images into the low-resolution (LR) MS images, resulting in texture-rich MS images. Though existing deep learning (DL)-based techniques have made impressive performance compared with traditional algorithms, they still face challenges in accurately restoring high-frequency details in MS images, thus limiting overall pan-sharpening performance. In addition, reference high-resolution (HR) MS images are often underutilized, typically serving only as training labels. In this work, we present a general high-frequency enhancement framework for pan-sharpening, which is implemented through a cooperative optimization strategy using mutual information (MI) maximization and contrastive learning. Specifically, our model comprises two fundamental modules: the high-frequency feature alignment (HFFA) module and the high-frequency detail calibration (HFDC) module. The first employs MI maximization to align the high-frequency semantic statistical distribution between PAN images and reference HRMS images. The latter is designed to calibrate the high-frequency components of MS modality under the guidance of the PAN counterparts through the contrastive learning constraint, thereby producing more accurate high-frequency information on MS modality. By integrating the calibrated high-frequency features of MS modality and those of PAN modality, we can obtain a more comprehensive and precise high-frequency feature representation of these two modalities, facilitating the reconstruction of LRMS images. Our model, incorporating the aforementioned key elements, significantly surpasses other state-of-the-art (SOTA) techniques across multiple satellite datasets in both quantitative and qualitative experiments. Moreover, the real-world full-resolution and cross-sensor assessments testify to its exceptional generalization capabilities. The code is available athttps://github.com/Vcocoi/CONet.

Contrastive adversarial training has shown great potential in enhancing model robustness and has been adopted in point cloud classification. There are varying spatial distributions and densities across different regions in point cloud data, which makes adversarial perturbations always exhibit non-uniform patterns of attack intensity and distribution in different regions. However, existing approaches always rely on uniform feature contrast without considering the granularity in the context of point cloud data, limiting their capacities to counter adversarial perturbations effectively. To address this issue, we propose a novel frequency-aware contrastive adversarial training framework, which considers feature contrast via a “divide-and-conquer” method. Specifically, we systematically “divide” point clouds into distinct frequency components and “conquer” feature contrast within each frequency band, which fosters fine-grained feature consistency learning and leads to more informative as well as robust representations. Besides, existing methods typically apply group-level contrastive learning, which emphasizes category-wise similarity but often overlooks the nuanced structural variations among instances. To remedy this, we incorporate instance-level contrastive learning to capture per-instance geometric variations. Moreover, a frequency-specific hard-masked sample generation module is designed to construct challenging sample pairs by masking keypoint features in each frequency band, thereby promoting the model to learn more robust feature representations. Extensive experiments on multiple benchmark datasets demonstrate that our proposed method significantly outperforms existing state-of-the-art approaches in adversarial robustness for point cloud classification. The code is available on DiCon-FAT.

Learning-based methods for underwater image enhancement (UWIE) have undergone extensive exploration. However, learning-based models are usually vulnerable to adversarial examples so as the UWIE models. To the best of our knowledge, there is no comprehensive study on the adversarial robustness of UWIE models, which indicates that UWIE models are potentially under the threat of adversarial attacks. In this paper, we propose a general adversarial attack protocol. We make a first attempt to conduct adversarial attacks on five well-designed UWIE models on three common underwater image benchmark datasets. Considering the scattering and absorption of light in the underwater environment, there exists a strong correlation between color correction and underwater image enhancement. On the basis of that, we also design two effective UWIE-oriented adversarial attack methods, Pixel Attack and Color Shift Attack targeting different color spaces. The results show that five models exhibit varying degrees of vulnerability to adversarial attacks and well-designed small perturbations on degraded images are capable of preventing UWIE models from generating enhanced results. In addition, we conduct adversarial training on these models and successfully mitigated the effectiveness of adversarial attacks. In summary, we reveal the adversarial vulnerability of UWIE models and propose a new evaluation dimension of UWIE models.

Due to the wavelength dependent light attenuation and scattering, the color of the underwater organism usually appears distorted. The existing underwater image enhancement methods mainly focus on designing networks capable of generating enhanced underwater organisms with fixed color. Due to the complexity of the underwater environment, ground truth labels are difficult to obtain, which results in the non-existence of perfect enhancement effects. Different from the existing methods, this paper proposes an algorithm with color enhancement and color fine-tuning (CECF) capabilities. The color enhancement behavior of CECF is the same as that of existing methods, aiming to restore the color of the distorted underwater organism. Beyond this general purpose, the color fine-tuning behavior of CECF can adjust the color of organisms in a controlled manner, which can generate enhanced organisms with diverse colors. To achieve this purpose, four processes are used in CECF. A supervised enhancement process learns the mapping from a distorted image to an enhanced image by the decomposition of color code. A self reconstruction process and a cross-reconstruction process are used for content-invariant learning. A color fine-tuning process is designed based on the guidance for obtaining various enhanced results with different colors. Experimental results have proven the enhancement ability and color fine-tuning ability of the proposed CECF. The source code is provided in https://github.com/Xiaofeng-life/CECF.

Existing research based on deep learning has extensively explored the problem of daytime image dehazing. However, few studies have considered the characteristics of nighttime hazy scenes. There are two distinctions between nighttime and daytime haze. First, there may be multiple active col-ored light sources with lower illumination intensity in night-time scenes, which may cause haze, glow and noise with localized, coupled and frequency inconsistent characteris-tics. Second, due to the domain discrepancy between simulated and real-world data, unrealistic brightness may occur when applying a dehazing model trained on simulated data to real-world data. To address the above two issues, we propose a semi-supervised model for real-world nighttime dehazing. First, the spatial attention and frequency spectrum filtering are implemented as a spatial-frequency do-main information interaction module to handle the first is-sue. Second, a pseudo-label-based retraining strategy and a local window-based brightness loss for semi-supervised training process is designed to suppress haze and glow while achieving realistic brightness. Experiments on public benchmarks validate the effectiveness of the proposed method and its superiority over state-of-the-art methods. The source code and Supplementary Materials are placed in the https://github.com/Xiaofeng-life/SFSNiD.

The research on the single image dehazing task has been widely explored. However, as far as we know, no comprehensive study has been conducted on the robustness of the well-trained dehazing models. Therefore, there is no evidence that the dehazing networks can resist malicious attacks. In this paper, we focus on designing a group of attack methods based on first order gradient to verify the robustness of the existing dehazing algorithms. By analyzing the general purpose of image dehazing task, four attack methods are proposed, which are predicted dehazed image attack, hazy layer mask attack, haze-free image attack and haze-preserved attack. The corresponding experiments are conducted on six datasets with different scales. Further, the defense strategy based on adversarial training is adopted for reducing the negative effects caused by malicious attacks. In summary, this paper defines a new challenging problem for the image dehazing area, which can be called as adversarial attack on dehazing networks (AADN). Code is available at https://github.com/Xiaofeng-life/AADN_Dehazing.

Pan-sharpening aims to super-resolve the low-resolution (LR) multispectral (MS) image under the guidance of a high-resolution (HR) panchromatic (PAN) image. Existing deep learning (DL)-based pan-sharpening methods usually adhere to a common philosophy of learning complementary information between MS and PAN images. Despite remarkable advances, few studies consider the band-private characteristics which differ greatly from band to band. An ideal MS image, however, is jointly determined by its diverse spectral bands, thus the accurate restoration of every band will benefit the pan-sharpening performance. In this work, we propose a novel yet effective solution to reconstruct the HRMS image by explicitly modulating every spectral band under the conditions of the PAN image. As a result, we design a spatially-adaptive spectral modulation network, dubbed SSMNet, which consists of three core designs: source-aware spectral modulator (SSM), cross-band information aggregation (CBIA) module, and cross-stage feature integration (CSFI) module. The first predicts a series of spatially-adaptive kernels to capture the local information of every spectral band. Followed by, the second is responsible for facilitating the information communication among various bands to guarantee continuous spectral representations. Furthermore, the third attends to integrate the cross-stage output features to produce the pan-sharpened result. In addition, we also introduce the histogram loss to constrain the band-wise distribution of the final fused products. Extensive experiments demonstrate that our SSMNet achieves favorable performance against other state-of-the-art (SOTA) methods on multiple satellite datasets. The code is available athttps://github.com/ez4lionky/SSMNet/.

The feature modulation mechanism has been demonstrated to be particularly well-suited for efficient network design and is rarely explored in remote sensing dehazing tasks. Moreover, we observe distinct patterns in haze distribution across the low-frequency (LF) and high-frequency (HF) components of haze images from various datasets. However, existing research rarely investigated the potential solution in the frequency domain. In response, we propose a novel spatial-frequency adaptive network (SFAN), which is mainly built by the proposed mixture of modulation experts (MoME) and decoupled frequency learning block (DFLB). Different from the fixed feature modulation design used in other tasks, the MoME adopts the mixture-of-expert mechanism to dynamically learn diverse contextual features of various granularities and scales in a sample-adaptive manner and then utilize them to perform elementwise local feature modulation. This pure convolution architecture enables our network to have superior performance and efficiency tradeoffs. Furthermore, the DFLB is devised to facilitate the LF global haze removal and reconstruction of HF local texture information. At the micro level, we first utilize a mask extractor (ME) to generate the frequency mask from the input hazy image, then employ a dual-branch decoupled learning unit to boost frequency learning, and finally develop a mixture of fusion experts (MoFE) to achieve HF and LF feature interaction. Extensive experiments on publicly available dehazing datasets demonstrate that our network performs superior performance while incurring lower computational costs. Compared to the state-of-the-art approach (DEA-Net), SFAN achieves, an average, 0.83-dB PSNR improvement on five remote sensing datasets but consumes only 51% of the FLOPs. The code will be available athttps://github.com/it-hao/SFAN.

On the one hand, the dehazing task is an ill-posedness problem, which means that no unique solution exists. On the other hand, the dehazing task should take into account the subjective factor, which is to give the user selectable dehazed images rather than a single result. Therefore, this paper proposes a multi-output dehazing network by introducing illumination controllable ability, called IC-Dehazing. The proposed IC-Dehazing can change the illumination intensity by adjusting the factor of the illumination controllable module, which is realized based on the interpretable Retinex model. Moreover, the backbone dehazing network of IC-Dehazing consists of a Transformer with double decoders for high-quality image restoration. Further, the prior-based loss function and unsupervised training strategy enable IC-Dehazing to complete the parameter learning process without the need for paired data. To demonstrate the effectiveness of the proposed IC-Dehazing, quantitative and qualitative experiments are conducted. Code is available athttps://github.com/Xiaofeng-life/ICDehazing.

The presence of haze significantly reduces the quality of images. Researchers have designed a variety of algorithms for image dehazing (ID) to restore the quality of hazy images. However, there are few studies that summarize the deep learning (DL) based dehazing technologies. In this paper, we conduct a comprehensive survey on the recent proposed dehazing methods. Firstly, we conclude the commonly used datasets, loss functions and evaluation metrics. Secondly, we group the existing researches of ID into two major categories: supervised ID and unsupervised ID. The core ideas of various influential dehazing models are introduced. Finally, the open issues for future research on ID are pointed out.

In contrast to traditional dehazing methods, deep learning based single image dehazing (SID) algorithms have achieved better performances by creating a mapping function from haze to haze-free images. Usually, the images taken from the natural scenes have different haze levels, but deep SID algorithms only process the hazy images as one group. It makes the deep SID algorithms difficult to deal with the image set with some images having specific haze density. In this paper, a Discrete Haze Level Dehazing network (DHL-Dehaze), a very effective method to dehaze multiple different haze level images, is proposed. The proposed approach considers a single image dehazing problem as a multi-domain image-to-image translation, instead of grouping all hazy images into the same domain. DHL-Dehaze provides computational derivation to describe the role of different haze levels for image translation. To verify the proposed approach, we synthesize two largescale datasets with multiple haze level images based on the NYU-Depth and DIML/CVL datasets. The experiments show that DHL-Dehaze can obtain excellent quantitative and qualitative dehazing results, especially when the haze concentration is high.