Image_Enhancement
-
Layer Decomposition and Morphological Reconstruction for Task-Oriented Infrared Image Enhancement
2025-06-29 18:10:05Siyuan Chai, Xiaodong Guo, Tong LiuAbstract
Infrared image helps improve the perception capabilities of autonomous driving in complex weather conditions such as fog, rain, and low light. However, infrared image often suffers from low contrast, especially in non-heat-emitting targets like bicycles, which significantly affects the performance of downstream high-level vision tasks. Furthermore, achieving contrast enhancement without amplifying noise and losing important information remains a challenge. To address these challenges, we propose a task-oriented infrared image enhancement method. Our approach consists of two key components: layer decomposition and saliency information extraction. First, we design an layer decomposition method for infrared images, which enhances scene details while preserving dark region features, providing more features for subsequent saliency information extraction. Then, we propose a morphological reconstruction-based saliency extraction method that effectively extracts and enhances target information without amplifying noise. Our method improves the image quality for object detection and semantic segmentation tasks. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods.
Abstract (translated)
红外图像有助于提高自动驾驶在复杂天气条件（如雾、雨和低光环境）下的感知能力。然而，红外图像常常存在对比度较低的问题，尤其是在非热辐射目标（如自行车）上，这严重影响了下游高级视觉任务的性能。此外，在不放大噪声并丢失重要信息的情况下实现对比度增强仍然是一项挑战。为了解决这些挑战，我们提出了一种面向任务的红外图像增强方法。我们的方法包括两个关键组成部分：层分解和显著性信息提取。 首先，我们设计了一种针对红外图像的分层分解方法，该方法在增强场景细节的同时保持暗区特征不变，从而为后续的显著性信息提取提供更多特征。然后，我们提出了一种基于形态重构的显著性抽取方法，可以有效地提取并增强目标信息而不放大噪声。我们的方法改善了物体检测和语义分割任务中的图像质量。 广泛的实验表明，与现有最先进的方法相比，我们的方法在性能上具有优势。
URL
https://arxiv.org/abs/2506.23353
PDF
-
ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning
2025-06-27 13:35:34Ming Zhao, Pingping Liu, Tongshun Zhang, Zhe ZhangAbstract
Low-light image enhancement presents two primary challenges: 1) Significant variations in low-light images across different conditions, and 2) Enhancement levels influenced by subjective preferences and user intent. To address these issues, we propose ReF-LLE, a novel personalized low-light image enhancement method that operates in the Fourier frequency domain and incorporates deep reinforcement learning. ReF-LLE is the first to integrate deep reinforcement learning into this domain. During training, a zero-reference image evaluation strategy is introduced to score enhanced images, providing reward signals that guide the model to handle varying degrees of low-light conditions effectively. In the inference phase, ReF-LLE employs a personalized adaptive iterative strategy, guided by the zero-frequency component in the Fourier domain, which represents the overall illumination level. This strategy enables the model to adaptively adjust low-light images to align with the illumination distribution of a user-provided reference image, ensuring personalized enhancement results. Extensive experiments on benchmark datasets demonstrate that ReF-LLE outperforms state-of-the-art methods, achieving superior perceptual quality and adaptability in personalized low-light image enhancement.
Abstract (translated)
低光图像增强面临两大主要挑战：1）在不同条件下，低光图像的变化显著；2）增强效果受主观偏好和用户意图的影响。为解决这些问题，我们提出了一种新颖的个性化低光图像增强方法——ReF-LLE（基于傅里叶频域的深度强化学习），该方法首次将深度强化学习技术应用于这一领域。在训练阶段，引入了零参考图像评估策略来评分经过增强后的图像，并提供奖励信号以引导模型有效应对不同程度的低光条件。在推理阶段，ReF-LLE采用了一种个性化的自适应迭代策略，通过傅里叶域中的零频分量（代表整体照明水平）进行指导。该策略使模型能够根据用户提供的参考图像调整低光图像，使其符合用户的光照分布需求，从而实现个性化增强效果。在基准数据集上的广泛实验表明，ReF-LLE在个性化低光图像增强方面优于现有的最先进的方法，在感知质量和适应性上均表现出色。
URL
https://arxiv.org/abs/2506.22216
PDF
-
Learning to See in the Extremely Dark
2025-06-26 10:24:07Hai Jiang, Binhao Guan, Zhen Liu, Xiaohong Liu, Jian Yu, Zheng Liu, Songchen Han, Shuaicheng LiuAbstract
Learning-based methods have made promising advances in low-light RAW image enhancement, while their capability to extremely dark scenes where the environmental illuminance drops as low as 0.0001 lux remains to be explored due to the lack of corresponding datasets. To this end, we propose a paired-to-paired data synthesis pipeline capable of generating well-calibrated extremely low-light RAW images at three precise illuminance ranges of 0.01-0.1 lux, 0.001-0.01 lux, and 0.0001-0.001 lux, together with high-quality sRGB references to comprise a large-scale paired dataset named See-in-the-Extremely-Dark (SIED) to benchmark low-light RAW image enhancement approaches. Furthermore, we propose a diffusion-based framework that leverages the generative ability and intrinsic denoising property of diffusion models to restore visually pleasing results from extremely low-SNR RAW inputs, in which an Adaptive Illumination Correction Module (AICM) and a color consistency loss are introduced to ensure accurate exposure correction and color restoration. Extensive experiments on the proposed SIED and publicly available benchmarks demonstrate the effectiveness of our method. The code and dataset are available at this https URL.
Abstract (translated)
基于学习的方法在低光RAW图像增强方面取得了令人鼓舞的进展，然而由于缺乏相应的数据集，在环境照度降至0.0001勒克斯等极端黑暗场景中的能力仍有待探索。为此，我们提出了一种配对到配对的数据合成流水线，能够生成精确的极低光照度范围内的RAW图像（分别为0.01-0.1勒克斯、0.001-0.01勒克斯和0.0001-0.001勒克斯），并配备高质量的sRGB参考图，组成一个大规模配对数据集，命名为“极暗视界”（See-in-the-Extremely-Dark, SIED），以评估低光RAW图像增强方法。此外，我们还提出了一种基于扩散框架的方法，该框架利用了扩散模型的生成能力和固有的去噪特性，可以从极高噪声比（SNR）的RAW输入中恢复视觉上令人愉悦的结果，在此过程中引入了一个自适应光照校正模块（AICM）和一个色彩一致性损失函数，以确保准确的曝光校正和颜色还原。在我们提出的SIED以及公开可用基准上的广泛实验表明了该方法的有效性。代码和数据集可在此网址获得：[this https URL]。
URL
https://arxiv.org/abs/2506.21132
PDF
-
TDiR: Transformer based Diffusion for Image Restoration Tasks
2025-06-25 10:28:13Abbas Anwar, Mohammad Shullar, Ali Arshad Nasir, Mudassir Masood, Saeed AnwarAbstract
Images captured in challenging environments often experience various forms of degradation, including noise, color cast, blur, and light scattering. These effects significantly reduce image quality, hindering their applicability in downstream tasks such as object detection, mapping, and classification. Our transformer-based diffusion model was developed to address image restoration tasks, aiming to improve the quality of degraded images. This model was evaluated against existing deep learning methodologies across multiple quality metrics for underwater image enhancement, denoising, and deraining on publicly available datasets. Our findings demonstrate that the diffusion model, combined with transformers, surpasses current methods in performance. The results of our model highlight the efficacy of diffusion models and transformers in improving the quality of degraded images, consequently expanding their utility in downstream tasks that require high-fidelity visual data.
Abstract (translated)
在具有挑战性的环境中捕获的图像经常会遭受各种形式的质量退化，包括噪点、色偏、模糊和光线散射。这些影响显著降低了图像质量，妨碍了它们在下游任务（如物体检测、地图绘制和分类）中的应用效果。我们开发了一种基于变压器的扩散模型来解决图像恢复任务，旨在提升受损图像的质量。我们的模型在公开可用的数据集上进行了评估，针对水下图像增强、去噪和除雨等任务，并与现有的深度学习方法进行了多方面的质量指标对比。研究结果表明，结合了扩散模型和变压器的方法在性能上超越了当前的其他方法。我们的模型成果突显了扩散模型和变压器在提升受损图像质量方面的能力，从而扩大其在需要高保真视觉数据的下游任务中的应用范围。
URL
https://arxiv.org/abs/2506.20302
PDF
-
BSMamba: Brightness and Semantic Modeling for Long-Range Interaction in Low-Light Image Enhancement
2025-06-23 07:04:34Tongshun Zhang, Pingping Liu, Mengen Cai, Zijian Zhang, Yubing Lu, Qiuzhan ZhouAbstract
Current low-light image enhancement (LLIE) methods face significant limitations in simultaneously improving brightness while preserving semantic consistency, fine details, and computational efficiency. With the emergence of state-space models, particularly Mamba, image restoration has achieved remarkable performance, yet existing visual Mamba approaches flatten 2D images into 1D token sequences using fixed scanning rules, critically limiting interactions between distant tokens with causal relationships and constraining their ability to capture meaningful long-range dependencies. To address these fundamental limitations, we propose BSMamba, a novel visual Mamba architecture comprising two specially designed components: Brightness Mamba and Semantic Mamba. The Brightness Mamba revolutionizes token interaction patterns by prioritizing connections between distant tokens with similar brightness levels, effectively addressing the challenge of brightness restoration in LLIE tasks through brightness-guided selective attention. Complementing this, the Semantic Mamba establishes priority interactions between tokens sharing similar semantic meanings, allowing the model to maintain contextual consistency by connecting semantically related regions across the image, thus preserving the hierarchical nature of image semantics during enhancement. By intelligently modeling tokens based on brightness and semantic similarity rather than arbitrary scanning patterns, BSMamba transcends the constraints of conventional token sequencing while adhering to the principles of causal modeling. Extensive experiments demonstrate that BSMamba achieves state-of-the-art performance in LLIE while preserving semantic consistency.
Abstract (translated)
目前的低光图像增强（LLIE）方法在同时提高亮度、保持语义一致性、精细细节和计算效率方面面临重大限制。随着状态空间模型，特别是Mamba模型的出现，图像恢复已取得了显著性能，然而现有的视觉Mamba方法将2D图像通过固定的扫描规则扁平化为1D标记序列，这极大地限制了具有因果关系的远距离标记之间的交互，并约束了它们捕捉有意义的长程依赖性的能力。为了克服这些基本限制，我们提出了一种新的视觉Mamba架构BSMamba，该架构包含两个特别设计的组件：亮度Mamba和语义Mamba。 亮度Mamba通过优先连接具有相似亮度级别的远距离标记来革新令牌交互模式，这有效地解决了LLIE任务中的亮度恢复挑战，通过基于亮度的选择性注意机制实现。此外，语义Mamba则建立了共享类似语义含义的标记之间的优先交互，允许模型通过链接图像中相关区域来保持上下文一致性，从而在增强过程中保留图像语义的层次结构特性。 BSMamba通过根据亮度和语义相似性而非随意扫描模式智能地建模令牌，超越了传统令牌排序的约束，同时遵循因果建模的原则。广泛的实验表明，BSMamba在低光图像增强方面取得了最先进的性能，并且能够保持语义一致性。
URL
https://arxiv.org/abs/2506.18346
PDF
-
A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement
2025-06-23 06:11:55Muhammad Azeem Aslam, Hassan Khalid, Nisar AhmedAbstract
Low-light image enhancement remains a challenging task, particularly in the absence of paired training data. In this study, we present LucentVisionNet, a novel zero-shot learning framework that addresses the limitations of traditional and deep learning-based enhancement methods. The proposed approach integrates multi-scale spatial attention with a deep curve estimation network, enabling fine-grained enhancement while preserving semantic and perceptual fidelity. To further improve generalization, we adopt a recurrent enhancement strategy and optimize the model using a composite loss function comprising six tailored components, including a novel no-reference image quality loss inspired by human visual perception. Extensive experiments on both paired and unpaired benchmark datasets demonstrate that LucentVisionNet consistently outperforms state-of-the-art supervised, unsupervised, and zero-shot methods across multiple full-reference and no-reference image quality metrics. Our framework achieves high visual quality, structural consistency, and computational efficiency, making it well-suited for deployment in real-world applications such as mobile photography, surveillance, and autonomous navigation.
Abstract (translated)
低光图像增强依然是一个挑战性的任务，尤其是在缺乏配对训练数据的情况下。本研究中，我们提出了一种新的零样本学习框架——LucentVisionNet，旨在解决传统方法和基于深度学习的方法的局限性。该提出的方案结合了多尺度空间注意力机制与深层曲线估计网络，使图像能够进行精细化增强，并同时保持语义和感知保真度。为了进一步提高泛化能力，我们采用了一种递归增强策略，并使用一个包含六个定制组件的复合损失函数来优化模型，其中包括一种受人类视觉感知启发的新颖无参考图像质量损失。在配对和非配对基准数据集上的大量实验表明，LucentVisionNet在多个全参考和无参考图像质量度量标准下始终优于现有的监督、非监督以及零样本方法。 我们的框架实现了高质量的视觉效果、结构一致性及计算效率，在移动摄影、监控与自主导航等实际应用场景中表现出良好的适用性。
URL
https://arxiv.org/abs/2506.18323
PDF
-
Temperature calibration of surface emissivities with an improved thermal image enhancement network
2025-06-20 07:40:05Ning Chu, Siya Zheng, Shanqing Zhang, Li Li, Caifang Cai, Ali Mohammad-Djafari, Feng Zhao, Yuanbo SongAbstract
Infrared thermography faces persistent challenges in temperature accuracy due to material emissivity variations, where existing methods often neglect the joint optimization of radiometric calibration and image degradation. This study introduces a physically guided neural framework that unifies temperature correction and image enhancement through a symmetric skip-CNN architecture and an emissivity-aware attention module. The pre-processing stage segments the ROIs of the image and and initially corrected the firing rate. A novel dual-constrained loss function strengthens the statistical consistency between the target and reference regions through mean-variance alignment and histogram matching based on Kullback-Leibler dispersion. The method works by dynamically fusing thermal radiation features and spatial context, and the model suppresses emissivity artifacts while recovering structural details. After validating the industrial blower system under different conditions, the improved network realizes the dynamic fusion of thermal radiation characteristics and spatial background, with accurate calibration results in various industrial conditions.
Abstract (translated)
红外热成像技术在温度准确性方面面临持续挑战，主要是由于材料发射率的变化，而现有的方法往往忽视了辐射校准与图像退化联合优化的重要性。这项研究引入了一个物理引导的神经网络框架，通过对称跳跃式卷积神经网络（skip-CNN）架构和发射率感知注意力模块统一了温度修正与图像增强过程。在预处理阶段，该框架分割出感兴趣区域并初步调整了火线比率。一种新颖的双重约束损失函数增强了目标区域与参考区域之间的统计一致性，通过基于Kullback-Leibler散度的均值-方差对齐和直方图匹配实现。 该方法通过动态融合热辐射特征与空间上下文信息工作，并且模型能够抑制发射率伪影同时恢复结构细节。经过不同条件下工业鼓风机系统的验证后，改进后的网络实现了热辐射特性和空间背景的动态融合，在各种工业环境中均能提供精确的校准结果。
URL
https://arxiv.org/abs/2506.16803
PDF
-
Integrating Generative Adversarial Networks and Convolutional Neural Networks for Enhanced Traffic Accidents Detection and Analysis
2025-06-19 10:06:20Zhenghao Xi, Xiang Liu, Yaqi Liu, Yitong Cai, Yangyu ZhengAbstract
Accident detection using Closed Circuit Television (CCTV) footage is one of the most imperative features for enhancing transport safety and efficient traffic control. To this end, this research addresses the issues of supervised monitoring and data deficiency in accident detection systems by adapting excellent deep learning technologies. The motivation arises from rising statistics in the number of car accidents worldwide; this calls for innovation and the establishment of a smart, efficient and automated way of identifying accidents and calling for help to save lives. Addressing the problem of the scarcity of data, the presented framework joins Generative Adversarial Networks (GANs) for synthesizing data and Convolutional Neural Networks (CNN) for model training. Video frames for accidents and non-accidents are collected from YouTube videos, and we perform resizing, image enhancement and image normalisation pixel range adjustments. Three models are used: CNN, Fine-tuned Convolutional Neural Network (FTCNN) and Vision Transformer (VIT) worked best for detecting accidents from CCTV, obtaining an accuracy rate of 94% and 95%, while the CNN model obtained 88%. Such results show that the proposed framework suits traffic safety applications due to its high real-time accident detection capabilities and broad-scale applicability. This work lays the foundation for intelligent surveillance systems in the future for real-time traffic monitoring, smart city framework, and integration of intelligent surveillance systems into emergency management systems.
Abstract (translated)
使用闭路电视（CCTV）录像进行事故检测是提高交通安全和有效交通控制最重要的特征之一。为此，本研究通过采用先进的深度学习技术来解决事故检测系统中监督监控不足和数据缺乏的问题。这一动机源自全球汽车事故发生率上升的统计数据；这要求创新并建立一种智能、高效且自动化的识别事故并向外界求援的方法以拯救生命。 为了解决数据稀缺问题，所提出的框架结合了生成对抗网络（GANs）用于合成数据以及卷积神经网络（CNN）进行模型训练。从YouTube视频中收集到的交通事故和非交通事故视频帧进行了调整大小、图像增强及像素范围标准化处理。使用了三种模型：CNN、微调后的卷积神经网络（FTCNN）和视觉变换器（VIT），这些模型在识别CCTV中的事故时表现最佳，准确率分别达到了94%和95%，而CNN模型的准确率为88%。这样的结果表明所提出的框架适用于交通安全管理应用，因其具备高实时性事故检测能力和广泛的应用潜力。 这项工作为未来的智能监控系统奠定了基础，这些系统可用于实时交通监控、智慧城市框架以及将智能监控系统整合到紧急管理系统中。
URL
https://arxiv.org/abs/2506.16186
PDF
-
A Deep Learning Approach for Facial Attribute Manipulation and Reconstruction in Surveillance and Reconnaissance
2025-06-06 23:09:17Anees Nashath Shaik, Barbara Villarini, Vasileios ArgyriouAbstract
Surveillance systems play a critical role in security and reconnaissance, but their performance is often compromised by low-quality images and videos, leading to reduced accuracy in face recognition. Additionally, existing AI-based facial analysis models suffer from biases related to skin tone variations and partially occluded faces, further limiting their effectiveness in diverse real-world scenarios. These challenges are the results of data limitations and imbalances, where available training datasets lack sufficient diversity, resulting in unfair and unreliable facial recognition performance. To address these issues, we propose a data-driven platform that enhances surveillance capabilities by generating synthetic training data tailored to compensate for dataset biases. Our approach leverages deep learning-based facial attribute manipulation and reconstruction using autoencoders and Generative Adversarial Networks (GANs) to create diverse and high-quality facial datasets. Additionally, our system integrates an image enhancement module, improving the clarity of low-resolution or occluded faces in surveillance footage. We evaluate our approach using the CelebA dataset, demonstrating that the proposed platform enhances both training data diversity and model fairness. This work contributes to reducing bias in AI-based facial analysis and improving surveillance accuracy in challenging environments, leading to fairer and more reliable security applications.
Abstract (translated)
监控系统在安全和侦察中扮演着关键角色，但其性能常常因图像和视频质量低劣而受损，导致面部识别的准确性降低。此外，现有的基于人工智能的面部分析模型受肤色差异及部分遮挡脸部的影响而产生偏差，进一步限制了它们在多样化现实场景中的有效性。这些挑战源于数据限制和不平衡问题，现有训练数据集缺乏足够的多样性，从而导致不公平且不可靠的面部识别性能。 为了解决这些问题，我们提出了一种基于数据驱动平台的方法，通过生成合成训练数据来增强监控能力，并弥补数据集偏差。我们的方法利用深度学习技术进行面部属性操作与重建，使用自动编码器和生成对抗网络（GAN）创建多样化的高质量面部图像数据集。此外，该系统还整合了一个图像增强模块，以提高低分辨率或部分遮挡的面部在监控录像中的清晰度。 我们通过CelebA数据集验证了这种方法的有效性，结果表明所提出的平台可以提升训练数据多样性并改善模型公平性。这项工作有助于减少基于人工智能的面部分析中的偏差，并在充满挑战的环境中提升监控系统的准确性，从而为更公正和可靠的安防应用提供支持。
URL
https://arxiv.org/abs/2506.06578
PDF
-
Bidirectional Image-Event Guided Low-Light Image Enhancement
2025-06-06 14:28:17Zhanwen Liu, Huanna Song, Yang Wang, Nan Yang, Shangyu Xie, Yisheng An, Xiangmo ZhaoAbstract
Under extreme low-light conditions, traditional frame-based cameras, due to their limited dynamic range and temporal resolution, face detail loss and motion blur in captured images. To overcome this bottleneck, researchers have introduced event cameras and proposed event-guided low-light image enhancement algorithms. However, these methods neglect the influence of global low-frequency noise caused by dynamic lighting conditions and local structural discontinuities in sparse event data. To address these issues, we propose an innovative Bidirectional guided Low-light Image Enhancement framework (BiLIE). Specifically, to mitigate the significant low-frequency noise introduced by global illumination step changes, we introduce the frequency high-pass filtering-based Event Feature Enhancement (EFE) module at the event representation level to suppress the interference of low-frequency information, and preserve and highlight the high-frequency this http URL, we design a Bidirectional Cross Attention Fusion (BCAF) mechanism to acquire high-frequency structures and edges while suppressing structural discontinuities and local noise introduced by sparse event guidance, thereby generating smoother fused this http URL, considering the poor visual quality and color bias in existing datasets, we provide a new dataset (RELIE), with high-quality ground truth through a reliable enhancement scheme. Extensive experimental results demonstrate that our proposed BiLIE outperforms state-of-the-art methods by 0.96dB in PSNR and 0.03 in LPIPS.
Abstract (translated)
在极端低光条件下，传统的帧基摄像头由于其动态范围和时间分辨率有限，在捕捉图像时会面临细节丢失和运动模糊的问题。为克服这一瓶颈，研究人员引入了事件相机，并提出了基于事件的低光照图像增强算法。然而，这些方法忽略了由动态照明条件引起的全局低频噪声以及稀疏事件数据中局部结构不连续性的影响。为了应对这些问题，我们提出了一种创新的双向引导低光图像增强框架（BiLIE）。 具体而言，为减少由于全球照明变化步长引入的重大低频噪声，我们在事件表示层面引入了基于频率高通滤波的事件特征增强（EFE）模块来抑制低频信息的干扰，并保留和突出高频细节。同时，我们设计了一种双向交叉注意融合机制(BCAF)，以获取高频结构和边缘，同时抑制稀疏事件引导所引入的局部噪声及结构不连续性，从而生成更加平滑的融合图像。 此外，考虑到现有数据集中存在的视觉质量差以及色彩偏差的问题，我们提供了一个新的数据集(RELIE)，通过可靠增强方案来确保高质量的真实标签。广泛的实验结果表明，我们的BiLIE框架在PSNR指标上比当前最佳方法高出0.96dB，在LPIPS指标上高出0.03。
URL
https://arxiv.org/abs/2506.06120
PDF
-
OpenRR-5k: A Large-Scale Benchmark for Reflection Removal in the Wild
2025-06-05 18:03:39Jie Cai, Kangning Yang, Ling Ouyang, Lan Fu, Jiaming Ding, Jinglin Shen, Zibo MengAbstract
Removing reflections is a crucial task in computer vision, with significant applications in photography and image enhancement. Nevertheless, existing methods are constrained by the absence of large-scale, high-quality, and diverse datasets. In this paper, we present a novel benchmark for Single Image Reflection Removal (SIRR). We have developed a large-scale dataset containing 5,300 high-quality, pixel-aligned image pairs, each consisting of a reflection image and its corresponding clean version. Specifically, the dataset is divided into two parts: 5,000 images are used for training, and 300 images are used for validation. Additionally, we have included 100 real-world testing images without ground truth (GT) to further evaluate the practical performance of reflection removal methods. All image pairs are precisely aligned at the pixel level to guarantee accurate supervision. The dataset encompasses a broad spectrum of real-world scenarios, featuring various lighting conditions, object types, and reflection patterns, and is segmented into training, validation, and test sets to facilitate thorough evaluation. To validate the usefulness of our dataset, we train a U-Net-based model and evaluate it using five widely-used metrics, including PSNR, SSIM, LPIPS, DISTS, and NIQE. We will release both the dataset and the code on this https URL to facilitate future research in this field.
Abstract (translated)
移除图像中的反射是计算机视觉领域的一项重要任务，在摄影和图像增强方面有着广泛的应用。然而，现有的方法受到大规模、高质量且多样化的数据集缺乏的限制。在本文中，我们提出了一套用于单张图片去反射(Single Image Reflection Removal, SIRR)的新基准测试。为此，我们开发了一个包含5,300对高分辨率像素级对齐图像的数据集，每一对包括带有反射的原始图和对应的无反射干净图。 具体来说，该数据集被分为两部分：其中5,000张用于训练，另外300张用于验证。此外，我们还包含了一组100张实际场景下的测试图片（没有真实标签），以便进一步评估去反射方法的实用性能。所有的图像对都经过像素级精确对齐以保证监督信号的准确性。 该数据集涵盖了各种现实世界中的场景，包括多样的光照条件、物体类型和反射模式，并且按照训练、验证和测试三个部分进行划分，以便全面评估。 为了展示我们数据集的有效性，我们在U-Net基础上训练了一个模型，并使用五个常用的评价指标（PSNR、SSIM、LPIPS、DISTS、NIQE）进行了评测。我们将在这个网址发布该数据集及代码，以促进未来在该领域的研究工作。
URL
https://arxiv.org/abs/2506.05482
PDF
-
Degradation-Aware Image Enhancement via Vision-Language Classification
2025-06-05 17:42:01Jie Cai, Kangning Yang, Jiaming Ding, Lan Fu, Ling Ouyang, Jiang Li, Jinglin Shen, Zibo MengAbstract
Image degradation is a prevalent issue in various real-world applications, affecting visual quality and downstream processing tasks. In this study, we propose a novel framework that employs a Vision-Language Model (VLM) to automatically classify degraded images into predefined categories. The VLM categorizes an input image into one of four degradation types: (A) super-resolution degradation (including noise, blur, and JPEG compression), (B) reflection artifacts, (C) motion blur, or (D) no visible degradation (high-quality image). Once classified, images assigned to categories A, B, or C undergo targeted restoration using dedicated models tailored for each specific degradation type. The final output is a restored image with improved visual quality. Experimental results demonstrate the effectiveness of our approach in accurately classifying image degradations and enhancing image quality through specialized restoration models. Our method presents a scalable and automated solution for real-world image enhancement tasks, leveraging the capabilities of VLMs in conjunction with state-of-the-art restoration techniques.
Abstract (translated)
图像退化是各种实际应用中的一个常见问题，它会影响视觉质量并影响后续处理任务。在这项研究中，我们提出了一种新颖的框架，该框架采用视觉-语言模型（VLM）自动将受损图像分类为预定义类别。VLM将输入图像归类为四种降质类型之一：(A) 超分辨率退化（包括噪声、模糊和JPEG压缩），(B) 反射伪影，(C) 运动模糊，或 (D) 无明显退化（高质量图像）。一旦分类完成，被分配到类别 A、B 或 C 的图像将使用针对每种特定降质类型量身定制的模型进行目标修复。最终输出是视觉质量得到提升的恢复后的图像。 实验结果证明了我们的方法在准确分类图像退化和通过专门的修复技术提高图像质量方面的有效性。本方法为实际图像增强任务提供了一种可扩展且自动化的解决方案，利用了VLM与最先进的修复技术相结合的能力。
URL
https://arxiv.org/abs/2506.05450
PDF
-
Physics Informed Capsule Enhanced Variational AutoEncoder for Underwater Image Enhancement
2025-06-05 08:39:17Niki Martinel, Rita PucciAbstract
We present a novel dual-stream architecture that achieves state-of-the-art underwater image enhancement by explicitly integrating the Jaffe-McGlamery physical model with capsule clustering-based feature representation learning. Our method simultaneously estimates transmission maps and spatially-varying background light through a dedicated physics estimator while extracting entity-level features via capsule clustering in a parallel stream. This physics-guided approach enables parameter-free enhancement that respects underwater formation constraints while preserving semantic structures and fine-grained details. Our approach also features a novel optimization objective ensuring both physical adherence and perceptual quality across multiple spatial frequencies. To validate our approach, we conducted extensive experiments across six challenging benchmarks. Results demonstrate consistent improvements of $+0.5$dB PSNR over the best existing methods while requiring only one-third of their computational complexity (FLOPs), or alternatively, more than $+1$dB PSNR improvement when compared to methods with similar computational budgets. Code and data \textit{will} be available at this https URL.
Abstract (translated)
我们提出了一种新颖的双流架构，通过明确整合Jaffe-McGlamery物理模型与基于胶囊聚类的特征表示学习，实现了最先进的水下图像增强。我们的方法在专用物理估计器中同时估算传输图和空间变化的背景光，而在并行流中则通过胶囊聚类提取实体级特征。这种物理引导的方法能够在尊重水下成像约束的同时保持语义结构和细微细节，并且无需参数调整即可实现增强效果。此外，我们的方法还引入了一种新颖的优化目标，确保在整个多频空间频率上同时符合物理规律并保证感知质量。 为了验证我们提出的方法的有效性，我们在六个具有挑战性的基准数据集上进行了广泛的实验。结果表明，在仅使用现有最佳方法三分之一计算复杂度（FLOPs）的情况下，我们的方法在PSNR指标上的性能提升了0.5dB；而与具有类似计算预算的方法相比，则表现出超过1dB PSNR的改进。代码和数据将在此[URL]发布。 注：请用实际链接替换上述方括号中的“https URL”文本以提供准确的数据获取途径。
URL
https://arxiv.org/abs/2506.04753
PDF
-
A Poisson-Guided Decomposition Network for Extreme Low-Light Image Enhancement
2025-06-04 21:40:01Isha Rao, Sanjay GhoshAbstract
Low-light image denoising and enhancement are challenging, especially when traditional noise assumptions, such as Gaussian noise, do not hold in majority. In many real-world scenarios, such as low-light imaging, noise is signal-dependent and is better represented as Poisson noise. In this work, we address the problem of denoising images degraded by Poisson noise under extreme low-light conditions. We introduce a light-weight deep learning-based method that integrates Retinex based decomposition with Poisson denoising into a unified encoder-decoder network. The model simultaneously enhances illumination and suppresses noise by incorporating a Poisson denoising loss to address signal-dependent noise. Without prior requirement for reflectance and illumination, the network learns an effective decomposition process while ensuring consistent reflectance and smooth illumination without causing any form of color distortion. The experimental results demonstrate the effectiveness and practicality of the proposed low-light illumination enhancement method. Our method significantly improves visibility and brightness in low-light conditions, while preserving image structure and color constancy under ambient illumination.
Abstract (translated)
在低光照条件下对图像进行去噪和增强是一项挑战，特别是在传统噪声假设（如高斯噪声）不成立的情况下。实际上，在许多场景中，例如低光成像时，噪声是与信号相关的，并且更适合作为泊松噪声来表示。在这项工作中，我们针对极端低光环境下受到泊松噪声污染的图像去噪问题提出了解决方案。我们引入了一种基于轻量级深度学习的方法，该方法将Retinex分解技术与泊松去噪相结合，在一个统一的编码器-解码器网络中实现。 该模型通过加入处理信号相关噪声的泊松去噪损失来同时增强照明并抑制噪声。无需事先了解反射率和光照的情况下，网络可以学习有效且一致的分解过程，确保反射率的一致性和光照平滑性而不引起任何形式的颜色失真。实验结果证明了所提出低光照明增强方法的有效性和实用性。我们的方法显著提高了低光环境下的可见度和亮度，同时在环境光照条件下保持图像结构和颜色一致性。
URL
https://arxiv.org/abs/2506.04470
PDF
-
RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement
2025-05-30 15:26:58Raman Jha, Adithya Lenka, Mani Ramanagopal, Aswin Sankaranarayanan, Kaushik MitraAbstract
In nighttime conditions, high noise levels and bright illumination sources degrade image quality, making low-light image enhancement challenging. Thermal images provide complementary information, offering richer textures and structural details. We propose RT-X Net, a cross-attention network that fuses RGB and thermal images for nighttime image enhancement. We leverage self-attention networks for feature extraction and a cross-attention mechanism for fusion to effectively integrate information from both modalities. To support research in this domain, we introduce the Visible-Thermal Image Enhancement Evaluation (V-TIEE) dataset, comprising 50 co-located visible and thermal images captured under diverse nighttime conditions. Extensive evaluations on the publicly available LLVIP dataset and our V-TIEE dataset demonstrate that RT-X Net outperforms state-of-the-art methods in low-light image enhancement. The code and the V-TIEE can be found here this https URL.
Abstract (translated)
在夜间条件下，高噪音水平和明亮的照明源会降低图像质量，使得低光环境下的图像增强变得极具挑战性。热成像图提供互补信息，可以提供更多纹理和结构细节。我们提出了RT-X Net，这是一种交叉注意力网络，用于融合RGB和热图以进行夜间图像增强。我们利用自注意网络提取特征，并采用跨模态注意力机制将两种模式的信息有效集成起来。为了支持该领域的研究，我们引入了可见光-热成像图像增强评估（V-TIEE）数据集，包含在各种夜间条件下拍摄的50组位置对应的可见光和热图。通过公开可用的LLVIP数据集以及我们的V-TIEE数据集进行广泛测试后发现，RT-X Net 在低光照图像增强方面优于现有技术方法。该代码及V-TIEE数据集可在此网址获得：[此链接]（请将"[此链接]"替换为实际链接）。
URL
https://arxiv.org/abs/2505.24705
PDF
-
CURVE: CLIP-Utilized Reinforcement Learning for Visual Image Enhancement via Simple Image Processing
2025-05-29 05:09:13Yuka Ogino, Takahiro Toizumi, Atsushi ItoAbstract
Low-Light Image Enhancement (LLIE) is crucial for improving both human perception and computer vision tasks. This paper addresses two challenges in zero-reference LLIE: obtaining perceptually 'good' images using the Contrastive Language-Image Pre-Training (CLIP) model and maintaining computational efficiency for high-resolution images. We propose CLIP-Utilized Reinforcement learning-based Visual image Enhancement (CURVE). CURVE employs a simple image processing module which adjusts global image tone based on Bézier curve and estimates its processing parameters iteratively. The estimator is trained by reinforcement learning with rewards designed using CLIP text embeddings. Experiments on low-light and multi-exposure datasets demonstrate the performance of CURVE in terms of enhancement quality and processing speed compared to conventional methods.
Abstract (translated)
低光图像增强（LLIE）对于改善人类感知和计算机视觉任务至关重要。本文解决了零参考LLIE的两个挑战：使用对比语言-图像预训练（CLIP）模型获取感知上“良好”的图像，以及为高分辨率图像保持计算效率。我们提出了基于强化学习并利用CLIP的视觉图像增强方法（CURVE）。CURVE采用了一个简单的图像处理模块，该模块根据贝塞尔曲线调整全局图像色调，并通过迭代估计其处理参数。估计算法通过使用CLIP文本嵌入设计奖励的方式进行强化学习训练。 在低光和多曝光数据集上的实验表明，与传统方法相比，CURVE在增强质量和处理速度方面表现出色。
URL
https://arxiv.org/abs/2505.23102
PDF
-
URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration
2025-05-29 04:17:09Rui Xu, Yuzhen Niu, Yuezhou Li, Huangbiao Xu, Wenxi Liu, Yuzhong ChenAbstract
Existing low-light image enhancement (LLIE) and joint LLIE and deblurring (LLIE-deblur) models have made strides in addressing predefined degradations, yet they are often constrained by dynamically coupled degradations. To address these challenges, we introduce a Unified Receptance Weighted Key Value (URWKV) model with multi-state perspective, enabling flexible and effective degradation restoration for low-light images. Specifically, we customize the core URWKV block to perceive and analyze complex degradations by leveraging multiple intra- and inter-stage states. First, inspired by the pupil mechanism in the human visual system, we propose Luminance-adaptive Normalization (LAN) that adjusts normalization parameters based on rich inter-stage states, allowing for adaptive, scene-aware luminance modulation. Second, we aggregate multiple intra-stage states through exponential moving average approach, effectively capturing subtle variations while mitigating information loss inherent in the single-state mechanism. To reduce the degradation effects commonly associated with conventional skip connections, we propose the State-aware Selective Fusion (SSF) module, which dynamically aligns and integrates multi-state features across encoder stages, selectively fusing contextual information. In comparison to state-of-the-art models, our URWKV model achieves superior performance on various benchmarks, while requiring significantly fewer parameters and computational resources.
Abstract (translated)
现有的低光图像增强（LLIE）和联合低光图像增强与去模糊（LLIE-deblur）模型在解决预定义退化方面取得了显著进展，但它们通常受到动态耦合退化的限制。为了解决这些挑战，我们引入了一个具有多态视角的统一受体加权键值（URWKV）模型，该模型能够灵活有效地恢复低光图像中的降质情况。具体而言，我们将核心URWKV块定制化以感知和分析复杂的降质情况，并利用多个内部和跨阶段状态进行。 首先，受到人类视觉系统中瞳孔机制的启发，我们提出了一种基于丰富跨阶段状态调整归一化参数的亮度自适应归一化（LAN），它允许根据场景对亮度进行自适应调节。其次，通过指数移动平均方法聚合多个内部分阶段的状态，有效地捕捉细微的变化，并减少单一状态机制中固有的信息丢失。 为了降低传统跳过连接通常伴随的退化效应，我们提出了一个具有多态感知的选择性融合（SSF）模块，该模块能够在编码器阶段动态对齐和集成跨多级特征，选择性地融合上下文信息。与最先进的模型相比，我们的URWKV模型在各种基准测试中表现出优越性能的同时，还显著减少了所需的参数量和计算资源。 总结而言，通过引入具有创新机制的URWKV模型，我们旨在提供一种更灵活、更高效的方法来解决低光图像处理中的复杂退化问题。
URL
https://arxiv.org/abs/2505.23068
PDF
-
GL-PGENet: A Parameterized Generation Framework for Robust Document Image Enhancement
2025-05-28 06:37:06Zhihong Tang, Yang LiAbstract
Document Image Enhancement (DIE) serves as a critical component in Document AI systems, where its performance substantially determines the effectiveness of downstream tasks. To address the limitations of existing methods confined to single-degradation restoration or grayscale image processing, we present Global with Local Parametric Generation Enhancement Network (GL-PGENet), a novel architecture designed for multi-degraded color document images, ensuring both efficiency and robustness in real-world scenarios. Our solution incorporates three key innovations: First, a hierarchical enhancement framework that integrates global appearance correction with local refinement, enabling coarse-to-fine quality improvement. Second, a Dual-Branch Local-Refine Network with parametric generation mechanisms that replaces conventional direct prediction, producing enhanced outputs through learned intermediate parametric representations rather than pixel-wise mapping. This approach enhances local consistency while improving model generalization. Finally, a modified NestUNet architecture incorporating dense block to effectively fuse low-level pixel features and high-level semantic features, specifically adapted for document image characteristics. In addition, to enhance generalization performance, we adopt a two-stage training strategy: large-scale pretraining on a synthetic dataset of 500,000+ samples followed by task-specific fine-tuning. Extensive experiments demonstrate the superiority of GL-PGENet, achieving state-of-the-art SSIM scores of 0.7721 on DocUNet and 0.9480 on RealDAE. The model also exhibits remarkable cross-domain adaptability and maintains computational efficiency for high-resolution images without performance degradation, confirming its practical utility in real-world scenarios.
Abstract (translated)
文档图像增强（DIE）在文档人工智能系统中扮演着关键角色，其性能对下游任务的有效性有着重大影响。为了克服现有方法仅限于单一退化恢复或灰度图像处理的局限性，我们提出了一种全新的架构——全局与局部参数生成增强网络(GL-PGENet)，专门针对多退化的彩色文档图像，并确保在实际应用中的高效性和鲁棒性。 我们的解决方案包括三项关键创新： 1. **分层增强框架**：该框架结合了全球外观校正和局部细化，通过从粗到细的质量改进方法来提升图像质量。 2. **双分支局部精细化网络与参数生成机制**：替代传统直接预测的方法，这种机制采用学习得到的中间参数表示而不是像素级映射来产生增强输出。这种方法提升了局部一致性，并增强了模型的泛化能力。 3. **修改版NestUNet架构**：此架构融合了密集块，有效结合低层次像素特征和高层次语义特征，并特别针对文档图像的特点进行了优化。 此外，为了提高泛化性能，我们采用了一种两阶段训练策略：先在包含50万多个样本的合成数据集上进行大规模预训练，随后根据具体任务进行微调。广泛的实验表明GL-PGENet显著优于现有技术，在DocUNet和RealDAE测试集中分别达到了最先进的SSIM得分0.7721和0.9480。 该模型还展示了出色的跨域适应性，并且在处理高分辨率图像时，仍能保持计算效率而不影响性能表现，这进一步证实了其在实际场景中的实用价值。
URL
https://arxiv.org/abs/2505.22021
PDF
-
See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction
2025-05-27 02:40:49Yuan Wu, Zhiqiang Yan, Yigong Zhang, Xiang Li, ian YangAbstract
Occupancy prediction aims to estimate the 3D spatial distribution of occupied regions along with their corresponding semantic labels. Existing vision-based methods perform well on daytime benchmarks but struggle in nighttime scenarios due to limited visibility and challenging lighting conditions. To address these challenges, we propose \textbf{LIAR}, a novel framework that learns illumination-affined representations. LIAR first introduces Selective Low-light Image Enhancement (SLLIE), which leverages the illumination priors from daytime scenes to adaptively determine whether a nighttime image is genuinely dark or sufficiently well-lit, enabling more targeted global enhancement. Building on the illumination maps generated by SLLIE, LIAR further incorporates two illumination-aware components: 2D Illumination-guided Sampling (2D-IGS) and 3D Illumination-driven Projection (3D-IDP), to respectively tackle local underexposure and overexposure. Specifically, 2D-IGS modulates feature sampling positions according to illumination maps, assigning larger offsets to darker regions and smaller ones to brighter regions, thereby alleviating feature degradation in underexposed areas. Subsequently, 3D-IDP enhances semantic understanding in overexposed regions by constructing illumination intensity fields and supplying refined residual queries to the BEV context refinement process. Extensive experiments on both real and synthetic datasets demonstrate the superior performance of LIAR under challenging nighttime scenarios. The source code and pretrained models are available \href{this https URL}{here}.
Abstract (translated)
占用预测旨在估算被占据区域的3D空间分布及其相应的语义标签。现有的基于视觉的方法在白天基准测试中表现出色，但在夜间场景中由于能见度低和照明条件恶劣而面临挑战。为了解决这些问题，我们提出了**LIAR**（光照适应表示学习框架），该框架通过利用白天空间场景中的光照先验来改进夜间图像的处理。 具体来说，LIAR首先引入了选择性弱光图像增强(SLLIE)，它可以根据白天场景的光照先验自适应地判断夜间图像是否真正处于黑暗状态或照明充足，并进行针对性的整体提升。基于SLLIE生成的光照图，LIAR进一步整合了两个光照感知组件：2D光照引导采样(2D-IGS)和3D光照驱动投影(3D-IDP)，以分别解决局部曝光不足与过度曝光的问题。 具体而言，2D-IGS根据光照地图调节特征抽取的位置，在较暗的区域赋予较大的偏移值而在明亮区域给予较小的偏移值，从而缓解在曝光不足区域中的特征退化。随后，3D-IDP通过构建光照强度场和为BEV上下文细化过程提供精炼残差查询来提升过度曝光区域中的语义理解。 一系列在真实和合成数据集上的广泛实验表明，在具有挑战性的夜间场景中，LIAR展现出了卓越的性能。该框架的源代码和预训练模型可以在这里获取（原文链接）。
URL
https://arxiv.org/abs/2505.20641
PDF
-
Underwater Diffusion Attention Network with Contrastive Language-Image Joint Learning for Underwater Image Enhancement
2025-05-26 12:24:56Afrah Shaahid, Muzammil BehzadAbstract
Underwater images are often affected by complex degradations such as light absorption, scattering, color casts, and artifacts, making enhancement critical for effective object detection, recognition, and scene understanding in aquatic environments. Existing methods, especially diffusion-based approaches, typically rely on synthetic paired datasets due to the scarcity of real underwater references, introducing bias and limiting generalization. Furthermore, fine-tuning these models can degrade learned priors, resulting in unrealistic enhancements due to domain shifts. To address these challenges, we propose UDAN-CLIP, an image-to-image diffusion framework pre-trained on synthetic underwater datasets and enhanced with a customized classifier based on vision-language model, a spatial attention module, and a novel CLIP-Diffusion loss. The classifier preserves natural in-air priors and semantically guides the diffusion process, while the spatial attention module focuses on correcting localized degradations such as haze and low contrast. The proposed CLIP-Diffusion loss further strengthens visual-textual alignment and helps maintain semantic consistency during enhancement. The proposed contributions empower our UDAN-CLIP model to perform more effective underwater image enhancement, producing results that are not only visually compelling but also more realistic and detail-preserving. These improvements are consistently validated through both quantitative metrics and qualitative visual comparisons, demonstrating the model's ability to correct distortions and restore natural appearance in challenging underwater conditions.
Abstract (translated)
水下图像通常会受到光吸收、散射、色偏和伪影等复杂退化的严重影响，这使得增强对于有效物体检测、识别和场景理解至关重要。现有的方法，尤其是基于扩散的方法，由于缺乏真实的水下参考数据集而依赖于合成配对的数据集，从而引入了偏差并限制了泛化能力。此外，在进行微调时，这些模型会破坏已学习的先验知识，导致因领域偏移而导致不真实的增强效果。为了解决这些问题，我们提出了UDAN-CLIP，这是一种基于图像到图像扩散框架的方法，它在合成水下数据集上进行了预训练，并通过一个基于视觉语言模型的定制分类器、空间注意力模块以及一种新颖的CLIP-Diffusion损失函数得到了改进。该分类器保留了自然空气中的先验知识并为扩散过程提供了语义引导，而空间注意力模块则专注于纠正诸如雾气和低对比度等局部退化现象。所提出的CLIP-Diffusion损失进一步增强了视觉文本对齐，并有助于在增强过程中保持语义一致性。我们的贡献使UDAN-CLIP模型能够更有效地进行水下图像增强，不仅产生视觉上吸引人的结果，而且更加真实并保留了细节。这些改进通过定量指标和定性视觉对比得到了一致验证，展示了该模型能够在具有挑战性的水下条件下纠正失真并恢复自然外观的能力。
URL
https://arxiv.org/abs/2505.19895
PDF
