Image_Enhancement
-
SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain
2025-08-26 04:10:55Xin Tian, Yingtie Lei, Xiujun Zhang, Zimeng Li, Chi-Man Pun, Xuhang ChenAbstract
Recent learning-based underwater image enhancement (UIE) methods have advanced by incorporating physical priors into deep neural networks, particularly using the signal-to-noise ratio (SNR) prior to reduce wavelength-dependent attenuation. However, spatial domain SNR priors have two limitations: (i) they cannot effectively separate cross-channel interference, and (ii) they provide limited help in amplifying informative structures while suppressing noise. To overcome these, we propose using the SNR prior in the frequency domain, decomposing features into amplitude and phase spectra for better channel modulation. We introduce the Fourier Attention SNR-prior Transformer (FAST), combining spectral interactions with SNR cues to highlight key spectral components. Additionally, the Frequency Adaptive Transformer (FAT) bottleneck merges low- and high-frequency branches using a gated attention mechanism to enhance perceptual quality. Embedded in a unified U-shaped architecture, these modules integrate a conventional RGB stream with an SNR-guided branch, forming SFormer. Trained on 4,800 paired images from UIEB, EUVP, and LSUI, SFormer surpasses recent methods with a 3.1 dB gain in PSNR and 0.08 in SSIM, successfully restoring colors, textures, and contrast in underwater scenes.
Abstract (translated)
最近基于学习的水下图像增强（UIE）方法通过在深度神经网络中引入物理先验而取得了进展，特别是利用信噪比（SNR）先验来减少波长依赖性衰减。然而，在空间域中的SNR先验存在两个局限：(i) 它们无法有效分离跨通道干扰；(ii) 它们在放大信息结构的同时抑制噪声方面提供的帮助有限。为克服这些问题，我们提出在频域中使用SNR先验，并将特征分解为振幅和相位谱，以实现更好的通道调制。我们引入了傅立叶注意信噪比先验变换器（FAST），结合光谱交互与SNR线索，突出关键的频谱成分。此外，频率自适应变换器（FAT）瓶颈通过门控注意力机制将低频和高频分支合并起来以提升感知质量。这些模块嵌入统一的U形架构中，整合了传统的RGB流与由SNR引导的分支，形成了SFormer。在UIEB、EUVP和LSUI数据集中的4,800对图像上进行训练后，SFormer超越了近期方法，在PSNR方面提高了3.1 dB，并且SSIM提升了0.08，成功恢复了水下场景的颜色、纹理和对比度。
URL
https://arxiv.org/abs/2508.18664
PDF
-
ISALux: Illumination and Segmentation Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement
2025-08-25 10:47:18Raul Balmez, Alexandru Brateanu, Ciprian Orhei, Codruta Ancuti, Cosmin AncutiAbstract
We introduce ISALux, a novel transformer-based approach for Low-Light Image Enhancement (LLIE) that seamlessly integrates illumination and semantic priors. Our architecture includes an original self-attention block, Hybrid Illumination and Semantics-Aware Multi-Headed Self- Attention (HISA-MSA), which integrates illumination and semantic segmentation maps for en- hanced feature extraction. ISALux employs two self-attention modules to independently process illumination and semantic features, selectively enriching each other to regulate luminance and high- light structural variations in real-world scenarios. A Mixture of Experts (MoE)-based Feed-Forward Network (FFN) enhances contextual learning, with a gating mechanism conditionally activating the top K experts for specialized processing. To address overfitting in LLIE methods caused by distinct light patterns in benchmarking datasets, we enhance the HISA-MSA module with low-rank matrix adaptations (LoRA). Extensive qualitative and quantitative evaluations across multiple specialized datasets demonstrate that ISALux is competitive with state-of-the-art (SOTA) methods. Addition- ally, an ablation study highlights the contribution of each component in the proposed model. Code will be released upon publication.
Abstract (translated)
我们介绍了ISALux，这是一种基于变压器的新型方法，用于低光图像增强（LLIE），该方法无缝地整合了照明和语义先验知识。我们的架构包括一个独特的自注意模块——混合照明与语义感知多头自我注意力(HISA-MSA)，它结合了照明图和语义分割地图以进行增强特征提取。ISALux采用两个自注意模块分别处理照明和语义特性，通过选择性地丰富彼此来调节实际场景中的亮度和高光结构变化。基于专家混合（MoE）的前馈网络(FFN)增强了上下文学习，并使用门控机制有条件激活前K名专家进行专业化处理。 为了应对由于基准数据集中不同光照模式而导致低光图像增强方法过度拟合的问题，我们通过低秩矩阵适应(Low-rank matrix adaptation, LoRA)来改进HISA-MSA模块。在多个专业数据集上进行的广泛定性和定量评估表明，ISALux与当前最先进的(SOTA)方法具有竞争力。此外，消融研究强调了所提出模型中每个组件的作用。论文发布后将公开代码。
URL
https://arxiv.org/abs/2508.17885
PDF
-
Enhancing Underwater Images via Deep Learning: A Comparative Study of VGG19 and ResNet50-Based Approaches
2025-08-24 15:10:44Aoqi Li, Yanghui Song, Jichao Dao, Chengfu YangAbstract
This paper addresses the challenging problem of image enhancement in complex underwater scenes by proposing a solution based on deep learning. The proposed method skillfully integrates two deep convolutional neural network models, VGG19 and ResNet50, leveraging their powerful feature extraction capabilities to perform multi-scale and multi-level deep feature analysis of underwater images. By constructing a unified model, the complementary advantages of the two models are effectively integrated, achieving a more comprehensive and accurate image enhancement this http URL objectively evaluate the enhancement effect, this paper introduces image quality assessment metrics such as PSNR, UCIQE, and UIQM to quantitatively compare images before and after enhancement and deeply analyzes the performance of different models in different this http URL, to improve the practicality and stability of the underwater visual enhancement system, this paper also provides practical suggestions from aspects such as model optimization, multi-model fusion, and hardware selection, aiming to provide strong technical support for visual enhancement tasks in complex underwater environments.
Abstract (translated)
本文提出了一种基于深度学习的解决方案，旨在解决复杂水下场景中的图像增强难题。所提方法巧妙地结合了VGG19和ResNet50两个深度卷积神经网络模型，利用它们强大的特征提取能力对水下图像进行多尺度、多层次的深入特征分析。通过构建统一模型，有效整合了两者的互补优势，从而实现更加全面且准确的图像增强效果。 为了客观评估增强效果，本文引入了PSNR（峰值信噪比）、UCIQE（彩色图像质量评价指标）和UIQM（统一图像质量度量）等图像质量评估指标，以定量比较增强前后图像的效果，并深入分析不同模型在不同场景下的性能表现。 此外，为提升水下视觉增强系统的实用性和稳定性，本文还从模型优化、多模态融合以及硬件选择等方面提供了切实可行的建议，旨在为复杂水下环境中的视觉增强任务提供强有力的技术支持。
URL
https://arxiv.org/abs/2508.17397
PDF
-
Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables
2025-08-22 06:28:24Wontae Kim, Keuntek Lee, Nam Ik ChoAbstract
The image enhancement methods based on 3D lookup tables (3D LUTs) efficiently reduce both model size and runtime by interpolating pre-calculated values at the vertices. However, the 3D LUT methods have a limitation due to their lack of spatial information, as they convert color values on a point-by-point basis. Although spatial-aware 3D LUT methods address this limitation, they introduce additional modules that require a substantial number of parameters, leading to increased runtime as image resolution increases. To address this issue, we propose a method for generating image-adaptive LUTs by focusing on the redundant parts of the tables. Our efficient framework decomposes a 3D LUT into a linear sum of low-dimensional LUTs and employs singular value decomposition (SVD). Furthermore, we enhance the modules for spatial feature fusion to be more cache-efficient. Extensive experimental results demonstrate that our model effectively decreases both the number of parameters and runtime while maintaining spatial awareness and performance.
Abstract (translated)
基于三维查找表（3D LUT）的图像增强方法通过在顶点处插值预先计算的值，能够有效地减少模型大小和运行时间。然而，由于3D LUT方法缺乏空间信息，在处理颜色值时是逐点进行转换的，因此存在局限性。尽管具有空间感知能力的3D LUT方法解决了这一限制问题，但它们引入了需要大量参数的额外模块，并且随着图像分辨率的增加会导致运行时间显著延长。 为了解决这个问题，我们提出了一种生成适应于图像的LUT的方法，该方法专注于查找表中的冗余部分。我们的高效框架将一个3D LUT分解成低维LUT的线性组合，并使用奇异值分解（SVD）。此外，我们还增强了用于空间特征融合的模块以提高缓存效率。 大量的实验结果表明，我们的模型在减少参数数量和运行时间的同时，还能保持对空间信息的关注以及性能水平。
URL
https://arxiv.org/abs/2508.16121
PDF
-
AquaFeat: A Features-Based Image Enhancement Model for Underwater Object Detection
2025-08-17 12:22:18Emanuel C. Silva, Tatiana T. Schein, Stephanie L. Bri\~ao, Guilherme L. M. Costa, Felipe G. Oliveira, Gustavo P. Almeida, Eduardo L. Silva, Sam S. Devincenzi, Karina S. Machado, Paulo L. J. Drews-JrAbstract
The severe image degradation in underwater environments impairs object detection models, as traditional image enhancement methods are often not optimized for such downstream tasks. To address this, we propose AquaFeat, a novel, plug-and-play module that performs task-driven feature enhancement. Our approach integrates a multi-scale feature enhancement network trained end-to-end with the detector's loss function, ensuring the enhancement process is explicitly guided to refine features most relevant to the detection task. When integrated with YOLOv8m on challenging underwater datasets, AquaFeat achieves state-of-the-art Precision (0.877) and Recall (0.624), along with competitive mAP scores (mAP@0.5 of 0.677 and mAP@[0.5:0.95] of 0.421). By delivering these accuracy gains while maintaining a practical processing speed of 46.5 FPS, our model provides an effective and computationally efficient solution for real-world applications, such as marine ecosystem monitoring and infrastructure inspection.
Abstract (translated)
在水下环境中，图像质量严重退化会影响物体检测模型的性能，因为传统的图像增强方法往往没有针对此类下游任务进行优化。为了解决这一问题，我们提出了AquaFeat，这是一种新颖且即插即用的功能增强模块，旨在执行任务驱动型特征增强。我们的方法将多尺度特征增强网络与检测器的损失函数端到端集成，确保增强过程明确地指导那些对检测任务最为相关的特征进行优化。 当我们将AquaFeat与YOLOv8m在具有挑战性的水下数据集上结合使用时，在精度（Precision 0.877）和召回率（Recall 0.624）方面达到了业界领先水平，同时还在竞争性平均精确度分数（mAP@0.5为0.677，mAP@[0.5:0.95]为0.421）上表现出色。通过在保持每秒处理速度达46.5帧的实用性能的同时提供这些精度改进，我们的模型为实际应用提供了有效的且计算效率高的解决方案，例如海洋生态系统的监测和基础设施检查。
URL
https://arxiv.org/abs/2508.12343
PDF
-
Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement
2025-08-12 15:20:32Luyang Cao, Han Xu, Jian Zhang, Lei Qi, Jiayi Ma, Yinghuan Shi, Yang GaoAbstract
In low-light image enhancement, Retinex-based deep learning methods have garnered significant attention due to their exceptional interpretability. These methods decompose images into mutually independent illumination and reflectance components, allows each component to be enhanced separately. In fact, achieving perfect decomposition of illumination and reflectance components proves to be quite challenging, with some residuals still existing after decomposition. In this paper, we formally name these residuals as inter-component residuals (ICR), which has been largely underestimated by previous methods. In our investigation, ICR not only affects the accuracy of the decomposition but also causes enhanced components to deviate from the ideal outcome, ultimately reducing the final synthesized image quality. To address this issue, we propose a novel Inter-correction Retinex model (IRetinex) to alleviate ICR during the decomposition and enhancement stage. In the decomposition stage, we leverage inter-component residual reduction module to reduce the feature similarity between illumination and reflectance components. In the enhancement stage, we utilize the feature similarity between the two components to detect and mitigate the impact of ICR within each enhancement unit. Extensive experiments on three low-light benchmark datasets demonstrated that by reducing ICR, our method outperforms state-of-the-art approaches both qualitatively and quantitatively.
Abstract (translated)
在低光图像增强领域，基于Retinex的深度学习方法因其出色的可解释性而受到了广泛关注。这些方法将图像分解为相互独立的照明和反射分量，允许每个分量分别进行增强处理。然而，在实践中，实现照明和反射分量的理想分割证明是非常具有挑战性的，即使经过了分解操作之后仍会存在一些残差。在本文中，我们将这些残差正式命名为跨成分残差（ICR），而这一问题在过去的方法中并未得到充分重视。我们的研究发现，ICR不仅影响了分解除的准确性，还导致增强后的分量偏离理想效果，最终降低合成图像的质量。 为了解决这个问题，我们提出了一种新的互矫正Retinex模型（IRetinex）来减轻在分解和增强阶段中的跨成分残差问题。在分解阶段，我们利用跨成分残差减少模块来降低照明与反射分量之间的特征相似性；而在增强阶段，我们则通过分析两个分量间的特征相似性，在每个增强单元中检测并缓解ICR的影响。 我们在三个低光基准数据集上的大量实验表明，我们的方法通过减少ICR不仅在定性和定量评估上都超越了当前最先进的技术。
URL
https://arxiv.org/abs/2508.09009
PDF
-
MIND: A Noise-Adaptive Denoising Framework for Medical Images Integrating Multi-Scale Transformer
2025-08-11 10:00:51Tao Tang, Chengxu YangAbstract
The core role of medical images in disease diagnosis makes their quality directly affect the accuracy of clinical judgment. However, due to factors such as low-dose scanning, equipment limitations and imaging artifacts, medical images are often accompanied by non-uniform noise interference, which seriously affects structure recognition and lesion detection. This paper proposes a medical image adaptive denoising model (MI-ND) that integrates multi-scale convolutional and Transformer architecture, introduces a noise level estimator (NLE) and a noise adaptive attention module (NAAB), and realizes channel-spatial attention regulation and cross-modal feature fusion driven by noise perception. Systematic testing is carried out on multimodal public datasets. Experiments show that this method significantly outperforms the comparative methods in image quality indicators such as PSNR, SSIM, and LPIPS, and improves the F1 score and ROC-AUC in downstream diagnostic tasks, showing strong prac-tical value and promotional potential. The model has outstanding benefits in structural recovery, diagnostic sensitivity, and cross-modal robustness, and provides an effective solution for medical image enhancement and AI-assisted diagnosis and treatment.
Abstract (translated)
医学影像在疾病诊断中的核心作用使其质量直接影响临床判断的准确性。然而，由于低剂量扫描、设备限制和成像伪影等因素，医学影像常常伴随非均匀噪声干扰，严重影响结构识别和病变检测。本文提出了一种集成多尺度卷积和Transformer架构的医疗图像自适应去噪模型（MI-ND），引入了噪声水平估计器（NLE）和噪声自适应注意模块（NAAB），实现了基于噪声感知的通道空间注意力调节和跨模态特征融合。在多模态公共数据集上进行了系统的测试。实验结果表明，该方法在图像质量指标如PSNR、SSIM和LPIPS方面显著优于比较方法，并提高了下游诊断任务中的F1评分和ROC-AUC值，显示出较强的实际价值和推广潜力。该模型在结构恢复、诊断敏感性和跨模态鲁棒性方面具有突出优势，并为医学影像增强和人工智能辅助诊断与治疗提供了有效的解决方案。
URL
https://arxiv.org/abs/2508.07817
PDF
-
Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation
2025-08-07 07:58:40Xuanru Zhou, Cheng Li, Shuqiang Wang, Ye Li, Tao Tan, Hairong Zheng, Shanshan WangAbstract
Generative artificial intelligence (AI) is rapidly transforming medical imaging by enabling capabilities such as data synthesis, image enhancement, modality translation, and spatiotemporal modeling. This review presents a comprehensive and forward-looking synthesis of recent advances in generative modeling including generative adversarial networks (GANs), variational autoencoders (VAEs), diffusion models, and emerging multimodal foundation architectures and evaluates their expanding roles across the clinical imaging continuum. We systematically examine how generative AI contributes to key stages of the imaging workflow, from acquisition and reconstruction to cross-modality synthesis, diagnostic support, and treatment planning. Emphasis is placed on both retrospective and prospective clinical scenarios, where generative models help address longstanding challenges such as data scarcity, standardization, and integration across modalities. To promote rigorous benchmarking and translational readiness, we propose a three-tiered evaluation framework encompassing pixel-level fidelity, feature-level realism, and task-level clinical relevance. We also identify critical obstacles to real-world deployment, including generalization under domain shift, hallucination risk, data privacy concerns, and regulatory hurdles. Finally, we explore the convergence of generative AI with large-scale foundation models, highlighting how this synergy may enable the next generation of scalable, reliable, and clinically integrated imaging systems. By charting technical progress and translational pathways, this review aims to guide future research and foster interdisciplinary collaboration at the intersection of AI, medicine, and biomedical engineering.
Abstract (translated)
生成式人工智能（AI）正在通过实现数据合成、图像增强、模态转换和时空建模等功能，迅速改变医学成像领域。这篇综述全面而前瞻地总结了近年来在生成模型方面取得的最新进展，包括生成对抗网络（GANs）、变分自动编码器（VAEs）、扩散模型以及新兴多模式基础架构，并评估它们在整个临床影像链中的扩展作用。我们系统性地考察了生成式AI如何助力成像工作流程的关键阶段，从获取和重建到跨模态合成、诊断支持及治疗计划制定。该综述特别强调回顾性和前瞻性临床场景，在这些场景中，生成模型帮助解决长期存在的挑战，如数据不足、标准化以及不同模态之间的整合问题。 为了促进严格的基准测试和转化准备度，我们提出了一级评估框架，涵盖像素级保真度、特征级现实感及任务级的临床相关性。同时，我们也指出了将生成式AI应用于真实世界部署的关键障碍，包括在领域转移下的泛化能力、幻觉风险、数据隐私问题以及监管障碍。 最后，本文探讨了生成式AI与大规模基础模型融合的趋势，并强调这种协同作用如何可能催生下一代可扩展、可靠且临床集成的成像系统。通过绘制技术进步和转化路径，本综述旨在指导未来的研究并促进人工智能、医学及生物医学工程交叉领域的合作。
URL
https://arxiv.org/abs/2508.09177
PDF
-
AU-IQA: A Benchmark Dataset for Perceptual Quality Assessment of AI-Enhanced User-Generated Content
2025-08-07 03:55:11Shushi Wang, Chunyi Li, Zicheng Zhang, Han Zhou, Wei Dong, Jun Chen, Guangtao Zhai, Xiaohong LiuAbstract
AI-based image enhancement techniques have been widely adopted in various visual applications, significantly improving the perceptual quality of user-generated content (UGC). However, the lack of specialized quality assessment models has become a significant limiting factor in this field, limiting user experience and hindering the advancement of enhancement methods. While perceptual quality assessment methods have shown strong performance on UGC and AIGC individually, their effectiveness on AI-enhanced UGC (AI-UGC) which blends features from both, remains largely unexplored. To address this gap, we construct AU-IQA, a benchmark dataset comprising 4,800 AI-UGC images produced by three representative enhancement types which include super-resolution, low-light enhancement, and denoising. On this dataset, we further evaluate a range of existing quality assessment models, including traditional IQA methods and large multimodal models. Finally, we provide a comprehensive analysis of how well current approaches perform in assessing the perceptual quality of AI-UGC. The access link to the AU-IQA is this https URL.
Abstract (translated)
基于AI的图像增强技术已在各种视觉应用中广泛采用，显著提高了用户生成内容（UGC）的感知质量。然而，缺乏专门的质量评估模型已成为该领域的一个重要限制因素，这不仅影响用户体验，还阻碍了增强方法的进步。虽然感知质量评估方法在单独处理UGC和AIGC时表现出色，但对于结合两者特征的AI增强UGC（AI-UGC），其有效性尚未得到充分研究。 为了解决这一空白，我们构建了一个名为AU-IQA的基准数据集，该数据集包含由三种代表性增强类型——超分辨率、低光增强及去噪产生的4,800张AI-UGC图像。在此数据集上，我们进一步评估了一系列现有的质量评估模型，包括传统的IQA方法和大型多模态模型。最后，我们提供了当前方法在评估AI-UGC感知质量方面的全面分析。 访问AU-IQA的数据集链接：[请参阅原文中的链接](https://example.com)（请替换为实际提供的URL）。
URL
https://arxiv.org/abs/2508.05016
PDF
-
RetinexDual: Retinex-based Dual Nature Approach for Generalized Ultra-High-Definition Image Restoration
2025-08-06 18:15:05Mohab Kishawy, Ali Abdellatif Hussein, Jun ChenAbstract
Advancements in image sensing have elevated the importance of Ultra-High-Definition Image Restoration (UHD IR). Traditional methods, such as extreme downsampling or transformation from the spatial to the frequency domain, encounter significant drawbacks: downsampling induces irreversible information loss in UHD images, while our frequency analysis reveals that pure frequency-domain approaches are ineffective for spatially confined image artifacts, primarily due to the loss of degradation locality. To overcome these limitations, we present RetinexDual, a novel Retinex theory-based framework designed for generalized UHD IR tasks. RetinexDual leverages two complementary sub-networks: the Scale-Attentive maMBA (SAMBA) and the Frequency Illumination Adaptor (FIA). SAMBA, responsible for correcting the reflectance component, utilizes a coarse-to-fine mechanism to overcome the causal modeling of mamba, which effectively reduces artifacts and restores intricate details. On the other hand, FIA ensures precise correction of color and illumination distortions by operating in the frequency domain and leveraging the global context provided by it. Evaluating RetinexDual on four UHD IR tasks, namely deraining, deblurring, dehazing, and Low-Light Image Enhancement (LLIE), shows that it outperforms recent methods qualitatively and quantitatively. Ablation studies demonstrate the importance of employing distinct designs for each branch in RetinexDual, as well as the effectiveness of its various components.
Abstract (translated)
在图像传感技术的进步推动下，超高清图像恢复（UHD IR）的重要性日益增加。传统方法，如极端降采样或从空间域转换到频率域的方法，在实际应用中遇到了显著的局限性：降采样会导致超高清图像中的不可逆信息损失；而我们的频谱分析表明，纯粹基于频率域的方法对于处理局部化退化的图像缺陷无效，主要是因为它们丢失了损坏的具体位置信息。为了解决这些问题，我们提出了RetinexDual，这是一种新型框架，基于Retinex理论设计用于通用的UHD IR任务。 RetinexDual采用两个互补的子网络：尺度注意多级双边滤波器（Scale-Attentive maMBA, SAMBA）和频率光照适配器（Frequency Illumination Adaptor, FIA）。SAMBA负责校正反射分量，通过从粗到细的工作机制克服了mamba模型的因果限制，从而有效地减少了伪影并恢复细节。另一方面，FIA在频域中操作，并利用全局上下文来确保准确地纠正颜色和光照失真。 通过对雨线移除、模糊消除、雾霾去除以及低光图像增强（LLIE）这四个UHD IR任务进行评估，RetinexDual在定性和定量分析上都优于最近的方法。消融研究展示了在RetinexDual中为每个分支采用不同设计的重要性，并证明了其各个组件的有效性。
URL
https://arxiv.org/abs/2508.04797
PDF
-
Uncertainty-Aware Spatial Color Correlation for Low-Light Image Enhancement
2025-08-06 08:02:21Jin Kuang, Dong Liu, Yukuang Zhang, Shengsheng WangAbstract
Most existing low-light image enhancement approaches primarily focus on architectural innovations, while often overlooking the intrinsic uncertainty within feature representations particularly under extremely dark conditions where degraded gradient and noise dominance severely impair model reliability and causal reasoning. To address these issues, we propose U2CLLIE, a novel framework that integrates uncertainty-aware enhancement and spatial-color causal correlation modeling. From the perspective of entropy-based uncertainty, our framework introduces two key components: (1) An Uncertainty-Aware Dual-domain Denoise (UaD) Module, which leverages Gaussian-Guided Adaptive Frequency Domain Feature Enhancement (G2AF) to suppress frequency-domain noise and optimize entropy-driven representations. This module enhances spatial texture extraction and frequency-domain noise suppression/structure refinement, effectively mitigating gradient vanishing and noise dominance. (2) A hierarchical causality-aware framework, where a Luminance Enhancement Network (LEN) first performs coarse brightness enhancement on dark regions. Then, during the encoder-decoder phase, two asymmetric causal correlation modeling modules Neighborhood Correlation State Space (NeCo) and Adaptive Spatial-Color Calibration (AsC) collaboratively construct hierarchical causal constraints. These modules reconstruct and reinforce neighborhood structure and color consistency in the feature space. Extensive experiments demonstrate that U2CLLIE achieves state-of-the-art performance across multiple benchmark datasets, exhibiting robust performance and strong generalization across various scenes.
Abstract (translated)
大多数现有的低光图像增强方法主要集中在架构创新上，而常常忽略了在极端黑暗条件下特征表示内在不确定性的问题。在这种情况下，退化的梯度和噪声主导效应会严重损害模型的可靠性和因果推理能力。为解决这些问题，我们提出了一种新的框架U2CLLIE（Uncertainty-aware Enhancement and Spatial-Color Causal Correlation Modeling），该框架集成了基于不确定性的增强功能以及空间色彩因果关系建模。 从熵基不确定性视角出发，我们的框架引入了两个关键组件： 1. **不确定性感知双域去噪模块 (Uncertainty-Aware Dual-domain Denoise, UaD)**：此模块利用高斯引导自适应频域特征增强（Gaussian-Guided Adaptive Frequency Domain Feature Enhancement, G2AF）来抑制频域噪声，并优化熵驱动表示。该模块增强了空间纹理提取以及频率域中的噪声抑制和结构细化能力，有效地缓解了梯度消失及噪声主导问题。 2. **层次因果框架**：在这一部分中，亮度增强网络（Luminance Enhancement Network, LEN）首先对暗区域进行粗略的亮度提升处理。然后，在编码器-解码器阶段，两个非对称因果关系建模模块“邻域相关状态空间”（Neighborhood Correlation State Space, NeCo）和“自适应空间色彩校准”（Adaptive Spatial-Color Calibration, AsC），共同构建了分层的因果约束。这些模块在特征空间中重建并增强了相邻结构和颜色一致性。 广泛的实验表明，U2CLLIE框架在多个基准数据集上取得了最先进的性能，在各种场景下均表现出强大的稳健性和泛化能力。
URL
https://arxiv.org/abs/2508.04176
PDF
-
Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement
2025-08-06 06:41:58Zheng Cheng, Wenri Wang, Guangyong Chen, Yakun Ju, Yihua Cheng, Zhisong Liu, Yanda Meng, Jintao SongAbstract
Underwater image enhancement (UIE) techniques aim to improve visual quality of images captured in aquatic environments by addressing degradation issues caused by light absorption and scattering effects, including color distortion, blurring, and low contrast. Current mainstream solutions predominantly employ multi-scale feature extraction (MSFE) mechanisms to enhance reconstruction quality through multi-resolution feature fusion. However, our extensive experiments demonstrate that high-quality image reconstruction does not necessarily rely on multi-scale feature fusion. Contrary to popular belief, our experiments show that single-scale feature extraction alone can match or surpass the performance of multi-scale methods, significantly reducing complexity. To comprehensively explore single-scale feature potential in underwater enhancement, we propose an innovative Single-Scale Decomposition Network (SSD-Net). This architecture introduces an asymmetrical decomposition mechanism that disentangles input image into clean layer along with degradation layer. The former contains scene-intrinsic information and the latter encodes medium-induced interference. It uniquely combines CNN's local feature extraction capabilities with Transformer's global modeling strengths through two core modules: 1) Parallel Feature Decomposition Block (PFDB), implementing dual-branch feature space decoupling via efficient attention operations and adaptive sparse transformer; 2) Bidirectional Feature Communication Block (BFCB), enabling cross-layer residual interactions for complementary feature mining and fusion. This synergistic design preserves feature decomposition independence while establishing dynamic cross-layer information pathways, effectively enhancing degradation decoupling capacity.
Abstract (translated)
水下图像增强（UIE）技术旨在通过解决由光吸收和散射效应引起的颜色失真、模糊和低对比度等退化问题，来改善在水环境中拍摄的图像的视觉质量。当前主流解决方案主要采用多尺度特征提取（MSFE）机制，通过多分辨率特征融合提升重建质量。然而，我们经过广泛实验发现，高质量的图像重构并不一定依赖于多尺度特征融合。与普遍看法相反，我们的实验表明，单尺度特征提取本身可以匹配甚至超过多尺度方法的性能，并显著降低复杂度。 为了全面探索单尺度特征在水下增强中的潜力，我们提出了一种创新的单尺度分解网络（SSD-Net）。该架构引入了不对称的分解机制，将输入图像分解为干净层和退化层。前者包含场景固有的信息，而后者编码介质引起的干扰。通过两个核心模块的独特结合——CNN的局部特征提取能力和Transformer的整体建模优势，该架构实现了：1）并行特征解耦块（PFDB），通过高效的注意力操作和自适应稀疏变换实现双分支特征空间解耦；2）双向特征通信块（BFCB），支持跨层残差交互以进行互补特征挖掘与融合。这种协同设计在保持特征分解独立性的同时建立了动态的跨层信息路径，有效增强了退化分离能力。
URL
https://arxiv.org/abs/2508.04123
PDF
-
CIVQLLIE: Causal Intervention with Vector Quantization for Low-Light Image Enhancement
2025-08-05 11:36:39Tongshun Zhang, Pingping Liu, Zhe Zhang, Qiuzhan ZhouAbstract
Images captured in nighttime scenes suffer from severely reduced visibility, hindering effective content perception. Current low-light image enhancement (LLIE) methods face significant challenges: data-driven end-to-end mapping networks lack interpretability or rely on unreliable prior guidance, struggling under extremely dark conditions, while physics-based methods depend on simplified assumptions that often fail in complex real-world scenarios. To address these limitations, we propose CIVQLLIE, a novel framework that leverages the power of discrete representation learning through causal reasoning. We achieve this through Vector Quantization (VQ), which maps continuous image features to a discrete codebook of visual tokens learned from large-scale high-quality images. This codebook serves as a reliable prior, encoding standardized brightness and color patterns that are independent of degradation. However, direct application of VQ to low-light images fails due to distribution shifts between degraded inputs and the learned codebook. Therefore, we propose a multi-level causal intervention approach to systematically correct these shifts. First, during encoding, our Pixel-level Causal Intervention (PCI) module intervenes to align low-level features with the brightness and color distributions expected by the codebook. Second, a Feature-aware Causal Intervention (FCI) mechanism with Low-frequency Selective Attention Gating (LSAG) identifies and enhances channels most affected by illumination degradation, facilitating accurate codebook token matching while enhancing the encoder's generalization performance through flexible feature-level intervention. Finally, during decoding, the High-frequency Detail Reconstruction Module (HDRM) leverages structural information preserved in the matched codebook representations to reconstruct fine details using deformable convolution techniques.
Abstract (translated)
夜间拍摄的图像由于能见度严重降低，影响了有效的内容感知。目前的低光图像增强（LLIE）方法面临重大挑战：数据驱动的端到端映射网络缺乏可解释性或依赖于不可靠的先验指导，在极其黑暗的情况下表现不佳；而基于物理的方法则依赖过于简化的假设，往往在复杂的现实世界场景中失效。为了解决这些局限性，我们提出了CIVQLLIE这一新框架，它通过因果推理利用离散表示学习的力量。我们通过向量量化（VQ）实现这一点，该技术将连续的图像特征映射到从大规模高质量图片中学得的视觉标记代码本中。这个代码本作为可靠的先验知识存在，编码了标准化的亮度和颜色模式，并且不受降质影响。 然而，直接将VQ应用于低光图像会导致受损输入与学习到的代码本之间的分布偏移问题。因此，我们提出了一种多层次因果干预的方法来系统地纠正这些偏差。首先，在编码阶段，我们的像素级因果干预（PCI）模块介入以对齐低级别特征和代码本期望的亮度及颜色分布。其次，具有低频选择性注意力门控（LSAG）的功能感知因果干预（FCI）机制识别并增强受照明降质影响最大的通道，从而促进准确的代码标记匹配，并通过灵活的功能级干预提升编码器的一般化性能。 最后，在解码阶段，高频细节重建模块（HDRM）利用在匹配代码本表示中保留的结构信息，使用可变形卷积技术来恢复精细细节。这种方法结合了数据驱动和物理模型的优势，同时避免了它们各自的缺点，为低光图像增强提供了一种新的有效途径。
URL
https://arxiv.org/abs/2508.03338
PDF
-
Exploring Fourier Prior and Event Collaboration for Low-Light Image Enhancement
2025-08-01 04:25:00Chunyan She, Fujun Han, Chengyu Fang, Shukai Duan, Lidan WangAbstract
The event camera, benefiting from its high dynamic range and low latency, provides performance gain for low-light image enhancement. Unlike frame-based cameras, it records intensity changes with extremely high temporal resolution, capturing sufficient structure information. Currently, existing event-based methods feed a frame and events directly into a single model without fully exploiting modality-specific advantages, which limits their performance. Therefore, by analyzing the role of each sensing modality, the enhancement pipeline is decoupled into two stages: visibility restoration and structure refinement. In the first stage, we design a visibility restoration network with amplitude-phase entanglement by rethinking the relationship between amplitude and phase components in Fourier space. In the second stage, a fusion strategy with dynamic alignment is proposed to mitigate the spatial mismatch caused by the temporal resolution discrepancy between two sensing modalities, aiming to refine the structure information of the image enhanced by the visibility restoration network. In addition, we utilize spatial-frequency interpolation to simulate negative samples with diverse illumination, noise and artifact degradations, thereby developing a contrastive loss that encourages the model to learn discriminative representations. Experiments demonstrate that the proposed method outperforms state-of-the-art models.
Abstract (translated)
事件相机由于其高动态范围和低延迟，在弱光图像增强方面表现出性能优势。与基于帧的相机不同，它以极高的时间分辨率记录强度变化，并捕获足够的结构信息。然而，现有的基于事件的方法直接将帧和事件输入到单一模型中，而没有充分利用每种模式特有的优点，这限制了它们的表现。 因此，通过分析每个感测模态的作用，增强管道被分解为两个阶段：可见性恢复与结构细化。在第一个阶段，我们设计了一个利用傅立叶空间中振幅和相位分量之间关系的重新思考的可见性恢复网络，并将其集成到一个称为“振幅-相位纠缠”的架构中。 在第二个阶段，为了缓解由于两种感测模式的时间分辨率差异造成的空间不匹配问题，我们提出了一种具有动态对齐策略的融合方法。这种方法旨在细化由可见性恢复网络增强的图像中的结构信息。 此外，我们使用空间频谱插值来模拟多种光照条件、噪声和瑕疵退化的负样本，从而开发出一种对比损失函数，鼓励模型学习更具判别性的表示形式。 实验表明，所提出的方法优于现有的最先进的模型。
URL
https://arxiv.org/abs/2508.00308
PDF
-
DACA-Net: A Degradation-Aware Conditional Diffusion Network for Underwater Image Enhancement
2025-07-30 09:16:07Chang Huang, Jiahang Cao, Jun Ma, Kieren Yu, Cong Li, Huayong Yang, Kaishun WuAbstract
Underwater images typically suffer from severe colour distortions, low visibility, and reduced structural clarity due to complex optical effects such as scattering and absorption, which greatly degrade their visual quality and limit the performance of downstream visual perception tasks. Existing enhancement methods often struggle to adaptively handle diverse degradation conditions and fail to leverage underwater-specific physical priors effectively. In this paper, we propose a degradation-aware conditional diffusion model to enhance underwater images adaptively and robustly. Given a degraded underwater image as input, we first predict its degradation level using a lightweight dual-stream convolutional network, generating a continuous degradation score as semantic guidance. Based on this score, we introduce a novel conditional diffusion-based restoration network with a Swin UNet backbone, enabling adaptive noise scheduling and hierarchical feature refinement. To incorporate underwater-specific physical priors, we further propose a degradation-guided adaptive feature fusion module and a hybrid loss function that combines perceptual consistency, histogram matching, and feature-level contrast. Comprehensive experiments on benchmark datasets demonstrate that our method effectively restores underwater images with superior colour fidelity, perceptual quality, and structural details. Compared with SOTA approaches, our framework achieves significant improvements in both quantitative metrics and qualitative visual assessments.
Abstract (translated)
水下图像通常会因散射和吸收等复杂光学效应而遭受严重的色彩失真、低可见度以及结构清晰度降低，这极大地损害了它们的视觉质量和下游视觉感知任务的表现。现有的增强方法往往难以适应各种退化条件，并且无法有效地利用特定于水下的物理先验知识。 在本文中，我们提出了一种基于退化意识的条件扩散模型，以自适应和稳健的方式提升水下图像的质量。给定一张受损的水下图像作为输入，首先使用轻量级双流卷积网络预测其退化程度，并生成一个连续的退化分数作为语义指导。在此基础上，我们引入了一个基于条件扩散的新式恢复网络，该网络以Swin UNet为骨干结构，实现了自适应噪声调度和分层特征细化。 为了将特定于水下的物理先验知识纳入考虑，我们还提出了一种退化引导的自适应特征融合模块以及一个结合了感知一致性、直方图匹配及特征级对比度的混合损失函数。 在基准数据集上的全面实验表明，我们的方法能够有效地恢复水下图像，使其色彩保真度、感知质量和结构细节达到优异水平。与最先进的方法相比，在定量指标和定性视觉评估中，我们框架均取得了显著改进。
URL
https://arxiv.org/abs/2507.22501
PDF
-
Evaluating Deepfake Detectors in the Wild
2025-07-29 15:17:00Viacheslav Pirogov, Maksim ArtemevAbstract
Deepfakes powered by advanced machine learning models present a significant and evolving threat to identity verification and the authenticity of digital media. Although numerous detectors have been developed to address this problem, their effectiveness has yet to be tested when applied to real-world data. In this work we evaluate modern deepfake detectors, introducing a novel testing procedure designed to mimic real-world scenarios for deepfake detection. Using state-of-the-art deepfake generation methods, we create a comprehensive dataset containing more than 500,000 high-quality deepfake images. Our analysis shows that detecting deepfakes still remains a challenging task. The evaluation shows that in fewer than half of the deepfake detectors tested achieved an AUC score greater than 60%, with the lowest being 50%. We demonstrate that basic image manipulations, such as JPEG compression or image enhancement, can significantly reduce model performance. All code and data are publicly available at this https URL.
Abstract (translated)
由先进机器学习模型驱动的Deepfakes对身份验证和数字媒体的真实性构成了一个重大且不断演变的威胁。尽管已经开发出了多种检测器来解决这一问题，但它们在应用于实际数据时的有效性尚未得到充分测试。在这项工作中，我们评估了现代Deepfake检测器，并引入了一种新颖的测试程序，旨在模拟现实世界中的Deepfake检测场景。使用最先进的Deepfake生成方法，我们创建了一个包含超过50万张高质量Deepfake图像的全面数据集。我们的分析表明，识别Deepfakes仍然是一项具有挑战性的任务。评估结果显示，在接受测试的所有Deepfake检测器中，不足一半达到了60%以上的AUC分数，最低者仅为50%。此外，我们证明了基本的图像操作，如JPEG压缩或图像增强，可以显著降低模型的表现。所有代码和数据均可在以下网址公开获取：[https URL]。
URL
https://arxiv.org/abs/2507.21905
PDF
-
Impact of Underwater Image Enhancement on Feature Matching
2025-07-29 11:45:47Jason M. Summers, Mark W. JonesAbstract
We introduce local matching stability and furthest matchable frame as quantitative measures for evaluating the success of underwater image enhancement. This enhancement process addresses visual degradation caused by light absorption, scattering, marine growth, and debris. Enhanced imagery plays a critical role in downstream tasks such as path detection and autonomous navigation for underwater vehicles, relying on robust feature extraction and frame matching. To assess the impact of enhancement techniques on frame-matching performance, we propose a novel evaluation framework tailored to underwater environments. Through metric-based analysis, we identify strengths and limitations of existing approaches and pinpoint gaps in their assessment of real-world applicability. By incorporating a practical matching strategy, our framework offers a robust, context-aware benchmark for comparing enhancement methods. Finally, we demonstrate how visual improvements affect the performance of a complete real-world algorithm -- Simultaneous Localization and Mapping (SLAM) -- reinforcing the framework's relevance to operational underwater scenarios.
Abstract (translated)
我们引入局部匹配稳定性和最远可匹配帧作为评估水下图像增强成功与否的量化指标。该增强过程旨在解决由光吸收、散射、海洋生物生长和垃圾引起的视觉退化问题。经过增强的图像在下游任务中起着关键作用，例如路径检测和自主导航，这些任务依赖于稳健的功能提取和帧匹配。为了评估增强技术对帧匹配性能的影响，我们提出了一种专为水下环境设计的新颖评价框架。通过基于指标的分析，我们识别现有方法的优势与局限，并指出它们在评估实际应用性方面存在的差距。通过纳入实用的匹配策略，我们的框架提供了一个稳健且上下文感知的基准，用于比较增强方法的效果。最后，我们展示了视觉改进如何影响一个完整的现实世界算法——同时定位和地图构建（SLAM）——的表现，从而强调了该框架在操作水下场景中的相关性。
URL
https://arxiv.org/abs/2507.21715
PDF
-
DRWKV: Focusing on Object Edges for Low-Light Image Enhancement
2025-07-24 17:24:59Xuecheng Bai, Yuxiang Wang, Boyu Hu, Qinyuan Jie, Chuanzhi Xu, Hongru Xiao, Kechen Li, Vera ChungAbstract
Low-light image enhancement remains a challenging task, particularly in preserving object edge continuity and fine structural details under extreme illumination degradation. In this paper, we propose a novel model, DRWKV (Detailed Receptance Weighted Key Value), which integrates our proposed Global Edge Retinex (GER) theory, enabling effective decoupling of illumination and edge structures for enhanced edge fidelity. Secondly, we introduce Evolving WKV Attention, a spiral-scanning mechanism that captures spatial edge continuity and models irregular structures more effectively. Thirdly, we design the Bilateral Spectrum Aligner (Bi-SAB) and a tailored MS2-Loss to jointly align luminance and chrominance features, improving visual naturalness and mitigating artifacts. Extensive experiments on five LLIE benchmarks demonstrate that DRWKV achieves leading performance in PSNR, SSIM, and NIQE while maintaining low computational complexity. Furthermore, DRWKV enhances downstream performance in low-light multi-object tracking tasks, validating its generalization capabilities.
Abstract (translated)
低光照图像增强仍然是一项具有挑战性的任务，尤其是在极端照明退化情况下保持物体边缘连续性和精细结构细节方面。在本文中，我们提出了一种新型模型DRWKV（Detailed Receptance Weighted Key Value），该模型集成了我们提出的全局边缘Retinex（GER）理论，能够有效地将光照和边缘结构解耦以增强边缘保真度。其次，我们引入了进化WKV注意力机制，这是一种螺旋扫描机制，可以更有效地捕捉空间边缘连续性并建模不规则结构。第三，我们设计了双边光谱对齐器（Bi-SAB）以及定制的MS2-Loss来共同对准亮度和色度特征，从而提高视觉自然度并减少伪影。在五个低光照图像增强基准数据集上的广泛实验表明，DRWKV在PSNR、SSIM和NIQE等指标上取得了领先性能，并且保持了较低的计算复杂度。此外，DRWKV还增强了下游任务中低光多目标跟踪的表现，验证了其泛化能力。
URL
https://arxiv.org/abs/2507.18594
PDF
-
Degradation-Consistent Learning via Bidirectional Diffusion for Low-Light Image Enhancement
2025-07-24 07:21:23Jinhong He, Minglong Xue, Zhipu Liu, Mingliang Zhou, Aoxiang Ning, Palaiahnakote ShivakumaraAbstract
Low-light image enhancement aims to improve the visibility of degraded images to better align with human visual perception. While diffusion-based methods have shown promising performance due to their strong generative capabilities. However, their unidirectional modelling of degradation often struggles to capture the complexity of real-world degradation patterns, leading to structural inconsistencies and pixel misalignments. To address these challenges, we propose a bidirectional diffusion optimization mechanism that jointly models the degradation processes of both low-light and normal-light images, enabling more precise degradation parameter matching and enhancing generation quality. Specifically, we perform bidirectional diffusion-from low-to-normal light and from normal-to-low light during training and introduce an adaptive feature interaction block (AFI) to refine feature representation. By leveraging the complementarity between these two paths, our approach imposes an implicit symmetry constraint on illumination attenuation and noise distribution, facilitating consistent degradation learning and improving the models ability to perceive illumination and detail degradation. Additionally, we design a reflection-aware correction module (RACM) to guide color restoration post-denoising and suppress overexposed regions, ensuring content consistency and generating high-quality images that align with human visual perception. Extensive experiments on multiple benchmark datasets demonstrate that our method outperforms state-of-the-art methods in both quantitative and qualitative evaluations while generalizing effectively to diverse degradation scenarios. Code at this https URL
Abstract (translated)
低光图像增强旨在改善降质图像的可视性，以更好地与人类视觉感知相匹配。虽然基于扩散的方法由于其强大的生成能力显示出有前景的表现，但它们对退化过程的一维建模往往难以捕捉现实世界中复杂多变的退化模式，导致结构上的不一致和像素错位问题。为了解决这些挑战，我们提出了一种双向扩散优化机制，该机制同时建模低光图像和正常光照图像的退化过程，从而实现更精确的退化参数匹配并提升生成质量。具体而言，在训练过程中，我们进行从低光到正常光照以及从正常光照回到低光的双向扩散，并引入自适应特征交互块（AFI）来优化特征表示。通过利用这两条路径之间的互补性，我们的方法在照明衰减和噪声分布上施加了隐式的对称约束，促进了退化学习的一致性和提高了模型感知照明及细节损失的能力。 此外，我们设计了一个反射感知校正模块（RACM），用于指导去噪后的颜色恢复，并抑制过曝区域的产生，确保内容一致性并生成高质量图像以匹配人类视觉感知。在多个基准数据集上的广泛实验表明，我们的方法无论是在定量还是定性评估中均超越了现有最佳方法，并且能够有效地泛化到各种退化场景。 代码可在该链接处访问：[此 URL]
URL
https://arxiv.org/abs/2507.18144
PDF
-
Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement
2025-07-24 03:35:20Xiaoran Sun, Liyan Wang, Cong Wang, Yeying Jin, Kin-man Lam, Zhixun Su, Yang Yang, Jinshan PanAbstract
Most existing low-light image enhancement (LLIE) methods rely on pre-trained model priors, low-light inputs, or both, while neglecting the semantic guidance available from normal-light images. This limitation hinders their effectiveness in complex lighting conditions. In this paper, we propose VLM-IMI, a novel framework that leverages large vision-language models (VLMs) with iterative and manual instructions (IMIs) for LLIE. VLM-IMI incorporates textual descriptions of the desired normal-light content as enhancement cues, enabling semantically informed restoration. To effectively integrate cross-modal priors, we introduce an instruction prior fusion module, which dynamically aligns and fuses image and text features, promoting the generation of detailed and semantically coherent outputs. During inference, we adopt an iterative and manual instruction strategy to refine textual instructions, progressively improving visual quality. This refinement enhances structural fidelity, semantic alignment, and the recovery of fine details under extremely low-light conditions. Extensive experiments across diverse scenarios demonstrate that VLM-IMI outperforms state-of-the-art methods in both quantitative metrics and perceptual quality. The source code is available at this https URL.
Abstract (translated)
大多数现有的低光图像增强（LLIE）方法依赖于预训练的模型先验、低光照输入或两者兼有，而忽略了正常光线图像提供的语义指导。这种限制阻碍了它们在复杂照明条件下的有效性。在这篇论文中，我们提出了VLM-IMI，这是一种新颖的框架，利用大型视觉语言模型（VLM）和迭代手动指令（IMIs）来进行低光图像增强。VLM-IMI整合了所需正常光照内容的文字描述作为增强提示，使语义引导的恢复成为可能。为了有效融合跨模态先验知识，我们引入了一个指令先验融合模块，该模块动态地对齐和融合图像与文本特征，促进生成详细且语义一致的输出。在推理过程中，我们采用迭代手动指令策略来优化文字说明，逐步提升视觉质量。这种细化增强了结构保真度、语义一致性，并改善了极低光照条件下的细节恢复能力。广泛的跨场景实验表明，VLM-IMI在定量指标和感知质量方面都优于最先进的方法。源代码可在提供的链接中获取。
URL
https://arxiv.org/abs/2507.18064
PDF
