Image_Enhancement
-
Diffusion Models for Low-Light Image Enhancement: A Multi-Perspective Taxonomy and Performance Analysis
2025-10-07 14:30:36Eashan Adhikarla, Yixin Liu, Brian D. DavisonAbstract
Low-light image enhancement (LLIE) is vital for safety-critical applications such as surveillance, autonomous navigation, and medical imaging, where visibility degradation can impair downstream task performance. Recently, diffusion models have emerged as a promising generative paradigm for LLIE due to their capacity to model complex image distributions via iterative denoising. This survey provides an up-to-date critical analysis of diffusion models for LLIE, distinctively featuring an in-depth comparative performance evaluation against Generative Adversarial Network and Transformer-based state-of-the-art methods, a thorough examination of practical deployment challenges, and a forward-looking perspective on the role of emerging paradigms like foundation models. We propose a multi-perspective taxonomy encompassing six categories: Intrinsic Decomposition, Spectral & Latent, Accelerated, Guided, Multimodal, and Autonomous; that map enhancement methods across physical priors, conditioning schemes, and computational efficiency. Our taxonomy is grounded in a hybrid view of both the model mechanism and the conditioning signals. We evaluate qualitative failure modes, benchmark inconsistencies, and trade-offs between interpretability, generalization, and inference efficiency. We also discuss real-world deployment constraints (e.g., memory, energy use) and ethical considerations. This survey aims to guide the next generation of diffusion-based LLIE research by highlighting trends and surfacing open research questions, including novel conditioning, real-time adaptation, and the potential of foundation models.
Abstract (translated)
低光图像增强（LLIE）对于安全关键型应用如监控、自主导航和医学成像至关重要，因为在这些领域中，能见度下降会损害下游任务的性能。最近，扩散模型作为LLIE的一个有前景的生成范例而兴起，这得益于它们通过迭代去噪来建模复杂图像分布的能力。本综述提供了一种对扩散模型在LLIE中的最新批判性分析，特别强调了与生成对抗网络和基于Transformer的方法进行深入性能比较、详尽的实际部署挑战评估以及对未来新兴范式（如基础模型）作用的前瞻性视角。 我们提出一个多角度分类法，涵盖六个类别：内在分解、频谱及潜在空间、加速、指导、多模态及自主性；这些类别跨越物理先验知识、条件方案和计算效率来映射增强方法。我们的分类法基于对模型机制与条件信号两者混合视图的理解。 我们评估了定性的失败模式、基准测试的一致性和解释性、泛化能力以及推理效率之间的权衡。此外，我们也讨论了实际部署的约束（如内存、能耗）和伦理问题。 本综述旨在通过强调趋势并揭示开放的研究问题来指导下一代基于扩散模型的LLIE研究，这些问题包括新颖的条件设置、实时适应及基础模型的应用潜力。
URL
https://arxiv.org/abs/2510.05976
PDF
-
Image Enhancement Based on Pigment Representation
2025-10-03 04:28:44Se-Ho Lee, Keunsoo Ko, Seung-Wook KimAbstract
This paper presents a novel and efficient image enhancement method based on pigment representation. Unlike conventional methods where the color transformation is restricted to pre-defined color spaces like RGB, our method dynamically adapts to input content by transforming RGB colors into a high-dimensional feature space referred to as \textit{pigments}. The proposed pigment representation offers adaptability and expressiveness, achieving superior image enhancement performance. The proposed method involves transforming input RGB colors into high-dimensional pigments, which are then reprojected individually and blended to refine and aggregate the information of the colors in pigment spaces. Those pigments are then transformed back into RGB colors to generate an enhanced output image. The transformation and reprojection parameters are derived from the visual encoder which adaptively estimates such parameters based on the content in the input image. Extensive experimental results demonstrate the superior performance of the proposed method over state-of-the-art methods in image enhancement tasks, including image retouching and tone mapping, while maintaining relatively low computational complexity and small model size.
Abstract (translated)
本文提出了一种基于色素表示的新型高效的图像增强方法。与传统的方法不同，传统的色彩变换受限于预定义的颜色空间（如RGB），我们的方法通过将RGB颜色动态转换为称为\textit{色素} 的高维特征空间来适应输入内容。提出的色素表示法提供了可调适性和表达性，在图像增强性能方面表现出色。 该方法首先将输入的RGB颜色转换成高维色素，然后单独重新投影并混合这些色素以优化和汇总色素空间中的色彩信息。随后，将这些色素再转换回RGB颜色，生成经过增强的输出图像。变换与重投影参数由视觉编码器自适应地根据输入图像的内容估计得出。 大量的实验结果表明，在包括图像修饰和色调映射在内的图像增强任务中，本文提出的方法在性能上优于现有的方法，并且保持了相对较低的计算复杂度和较小的模型大小。
URL
https://arxiv.org/abs/2510.02713
PDF
-
Adaptive Guided Upsampling for Low-light Image Enhancement
2025-10-02 19:05:29Angela Vivian Dcosta, Chunbo Song, Rafael RadkowskiAbstract
We introduce Adaptive Guided Upsampling (AGU), an efficient method for upscaling low-light images capable of optimizing multiple image quality characteristics at the same time, such as reducing noise and increasing sharpness. It is based on a guided image method, which transfers image characteristics from a guidance image to the target image. Using state-of-the-art guided methods, low-light images lack sufficient characteristics for this purpose due to their high noise level and low brightness, rendering suboptimal/not significantly improved images in the process. We solve this problem with multi-parameter optimization, learning the association between multiple low-light and bright image characteristics. Our proposed machine learning method learns these characteristics from a few sample images-pairs. AGU can render high-quality images in real time using low-quality, low-resolution input; our experiments demonstrate that it is superior to state-of-the-art methods in the addressed low-light use case.
Abstract (translated)
URL
https://arxiv.org/abs/2511.16623
PDF
-
LiDAR Point Cloud Colourisation Using Multi-Camera Fusion and Low-Light Image Enhancement
2025-09-30 06:56:11Pasindu Ranasinghe, Dibyayan Patra, Bikram Banerjee, Simit RavalAbstract
In recent years, the fusion of camera data with LiDAR measurements has emerged as a powerful approach to enhance spatial understanding. This study introduces a novel, hardware-agnostic methodology that generates colourised point clouds from mechanical LiDAR using multiple camera inputs, providing complete 360-degree coverage. The primary innovation lies in its robustness under low-light conditions, achieved through the integration of a low-light image enhancement module within the fusion pipeline. The system requires initial calibration to determine intrinsic camera parameters, followed by automatic computation of the geometric transformation between the LiDAR and cameras, removing the need for specialised calibration targets and streamlining the setup. The data processing framework uses colour correction to ensure uniformity across camera feeds before fusion. The algorithm was tested using a Velodyne Puck Hi-Res LiDAR and a four-camera configuration. The optimised software achieved real-time performance and reliable colourisation even under very low illumination, successfully recovering scene details that would otherwise remain undetectable.
Abstract (translated)
近年来，相机数据与激光雷达（LiDAR）测量的融合已成为增强空间理解力的一种强大方法。本研究介绍了一种新颖且硬件无关的方法，利用多台摄像机输入为机械激光雷达生成彩色点云，并提供完整的360度覆盖范围。该方法的主要创新在于其在低光条件下表现出的强大鲁棒性，通过在数据融合管道中集成一个低光图像增强模块实现。 系统需要进行初始校准以确定相机的内在参数，随后自动计算激光雷达与摄像机之间的几何变换，这消除了对特殊校准目标的需求，并简化了设置流程。该数据处理框架采用颜色校正技术，在点云融合前确保来自各摄像头的数据具有一致性。 算法使用Velodyne Puck Hi-Res LiDAR和四相机配置进行了测试。优化后的软件实现了实时性能，并在极低光照条件下也能实现可靠的彩色化，成功地恢复了原本可能无法检测到的场景细节。
URL
https://arxiv.org/abs/2509.25859
PDF
-
FlowLUT: Efficient Image Enhancement via Differentiable LUTs and Iterative Flow Matching
2025-09-28 03:22:01Liubing Hu, Chen Wu, Anrui Wang, Dianjie Lu, Guijuan Zhang, Zhuoran ZhengAbstract
Deep learning-based image enhancement methods face a fundamental trade-off between computational efficiency and representational capacity. For example, although a conventional three-dimensional Look-Up Table (3D LUT) can process a degraded image in real time, it lacks representational flexibility and depends solely on a fixed prior. To address this problem, we introduce FlowLUT, a novel end-to-end model that integrates the efficiency of LUTs, multiple priors, and the parameter-independent characteristic of flow-matched reconstructed images. Specifically, firstly, the input image is transformed in color space by a collection of differentiable 3D LUTs (containing a large number of 3D LUTs with different priors). Subsequently, a lightweight content-aware dynamically predicts fusion weights, enabling scene-adaptive color correction with $\mathcal{O}(1)$ complexity. Next, a lightweight fusion prediction network runs on multiple 3D LUTs, with $\mathcal{O}(1)$ complexity for scene-adaptive color this http URL, to address the inherent representation limitations of LUTs, we design an innovative iterative flow matching method to restore local structural details and eliminate artifacts. Finally, the entire model is jointly optimized under a composite loss function enforcing perceptual and structural fidelity. Extensive experimental results demonstrate the effectiveness of our method on three benchmarks.
Abstract (translated)
基于深度学习的图像增强方法面临着计算效率和表示能力之间的基本权衡。例如，传统的三维查找表（3D LUT）可以在实时处理降质图像的同时缺乏灵活性，并且仅依赖于固定的先验条件。为了应对这一问题，我们引入了FlowLUT，这是一种新颖的端到端模型，它集成了LUTs的效率、多种先验以及流匹配重建图像的参数独立特性。 具体来说，首先输入图像通过一系列可微分的3D LUT（包含具有不同先验条件的大量3D LUT）在颜色空间中进行转换。随后，一个轻量级的内容感知模块动态地预测融合权重，以实现场景适应性的色彩校正，并且其复杂度为$\mathcal{O}(1)$。接下来，轻量级的融合预测网络运行于多个3D LUT之上，同样具有$\mathcal{O}(1)$复杂度进行场景适应性颜色处理。 此外，为了克服LUT固有的表示限制，我们设计了一种创新性的迭代流匹配方法，用于恢复局部结构细节并消除伪影。最后，整个模型在复合损失函数下共同优化该函数强制执行感知和结构保真度。广泛的实验结果证明了我们的方法在三个基准测试中的有效性。
URL
https://arxiv.org/abs/2509.23608
PDF
-
StrCGAN: A Generative Framework for Stellar Image Restoration
2025-09-24 06:42:32Shantanusinh ParmarAbstract
We introduce StrCGAN (Stellar Cyclic GAN), a generative model designed to enhance low-resolution astrophotography images. Our goal is to reconstruct high-fidelity ground truth-like representations of celestial objects, a task that is challenging due to the limited resolution and quality of small-telescope observations such as the MobilTelesco dataset. Traditional models such as CycleGAN provide a foundation for image-to-image translation but are restricted to 2D mappings and often distort the morphology of stars and galaxies. To overcome these limitations, we extend the CycleGAN framework with three key innovations: 3D convolutional layers to capture volumetric spatial correlations, multi-spectral fusion to align optical and near-infrared (NIR) domains, and astrophysical regularization modules to preserve stellar morphology. Ground-truth references from multi-mission all-sky surveys spanning optical to NIR guide the training process, ensuring that reconstructions remain consistent across spectral bands. Together, these components allow StrCGAN to generate reconstructions that are not only visually sharper but also physically consistent, outperforming standard GAN models in the task of astrophysical image enhancement.
Abstract (translated)
我们引入了StrCGAN（Stellar Cyclic GAN），这是一种生成模型，旨在提升低分辨率的天文摄影图像。我们的目标是重建高质量的真实地面观测水平的天体对象表示，这一任务由于小型望远镜观测如MobilTelesco数据集所具有的有限分辨率和质量而变得极具挑战性。传统的模型如CycleGAN为图像到图像转换提供了基础，但它们局限于二维映射，并且经常扭曲恒星和星系的形态。为了克服这些限制，我们在CycleGAN框架上引入了三项关键创新：三维卷积层用于捕捉体积空间相关性、多光谱融合以对齐光学和近红外（NIR）领域以及天体物理学正则化模块来保持恒星星形结构。来自覆盖从光学到NIR波段的多个任务全天调查的真实参考数据指导训练过程，确保重建在不同光谱带之间的一致性。这些组件共同使StrCGAN能够生成不仅视觉上更加清晰、而且物理一致性更高的重构图像，在天体物理学图像增强的任务中超越了标准GAN模型的表现。
URL
https://arxiv.org/abs/2509.19805
PDF
-
FloorSAM: SAM-Guided Floorplan Reconstruction with Semantic-Geometric Fusion
2025-09-19 08:27:10Han Ye, Haofu Wang, Yunchi Zhang, Jiangjian Xiao, Yuqiang Jin, Jinyuan Liu, Wen-An Zhang, Uladzislau Sychou, Alexander Tuzikov, Vladislav Sobolevskii, Valerii Zakharov, Boris Sokolov, Minglei FuAbstract
Reconstructing building floor plans from point cloud data is key for indoor navigation, BIM, and precise measurements. Traditional methods like geometric algorithms and Mask R-CNN-based deep learning often face issues with noise, limited generalization, and loss of geometric details. We propose FloorSAM, a framework that integrates point cloud density maps with the Segment Anything Model (SAM) for accurate floor plan reconstruction from LiDAR data. Using grid-based filtering, adaptive resolution projection, and image enhancement, we create robust top-down density maps. FloorSAM uses SAM's zero-shot learning for precise room segmentation, improving reconstruction across diverse layouts. Room masks are generated via adaptive prompt points and multistage filtering, followed by joint mask and point cloud analysis for contour extraction and regularization. This produces accurate floor plans and recovers room topological relationships. Tests on Giblayout and ISPRS datasets show better accuracy, recall, and robustness than traditional methods, especially in noisy and complex settings. Code and materials: this http URL.
Abstract (translated)
从点云数据重建建筑楼层平面图是室内导航、BIM（建筑信息建模）和精确测量的关键。传统的几何算法及基于Mask R-CNN的深度学习方法在处理噪声问题时通常面临挑战，且存在泛化能力有限和几何细节丢失的问题。我们提出了FloorSAM框架，该框架将点云密度图与分割任何东西模型（Segment Anything Model, SAM）结合，用于从LiDAR数据中准确重建楼层平面图。 通过基于网格的过滤、自适应分辨率投影以及图像增强方法，我们创建了稳健的顶部视角密度图。FloorSAM利用SAM的零样本学习能力进行精确房间分割，在各种布局下提高重建精度。房间掩码是通过自适应提示点和多级过滤生成的，并随后结合掩码与点云分析提取轮廓并进行正则化处理。这种方法产生准确的楼层平面图，同时恢复房间拓扑关系。 在Giblayout和ISPRS数据集上的测试显示，FloorSAM在准确性、召回率及鲁棒性方面优于传统方法，特别是在嘈杂和复杂环境中表现尤为出色。代码与材料可在[此链接](http://this.http.url)获取。
URL
https://arxiv.org/abs/2509.15750
PDF
-
Recent Advancements in Microscopy Image Enhancement using Deep Learning: A Survey
2025-09-18 19:03:41Debasish Dutta, Neeharika Sonowal, Risheraj Barauh, Deepjyoti Chetia, Sanjib Kr KalitaAbstract
Microscopy image enhancement plays a pivotal role in understanding the details of biological cells and materials at microscopic scales. In recent years, there has been a significant rise in the advancement of microscopy image enhancement, specifically with the help of deep learning methods. This survey paper aims to provide a snapshot of this rapidly growing state-of-the-art method, focusing on its evolution, applications, challenges, and future directions. The core discussions take place around the key domains of microscopy image enhancement of super-resolution, reconstruction, and denoising, with each domain explored in terms of its current trends and their practical utility of deep learning.
Abstract (translated)
显微图像增强在理解生物细胞和材料的微观细节方面扮演着关键角色。近年来，借助深度学习方法，在显微图像增强领域取得了显著进展。本综述论文旨在概述这一迅速发展的最新技术状态，重点探讨其发展历程、应用、挑战以及未来方向。核心讨论围绕超分辨率、重建和去噪这三个显微图像增强的关键领域展开，每个领域的当前趋势及其在实际中的深度学习实用性都将得到详细探索。
URL
https://arxiv.org/abs/2509.15363
PDF
-
FunKAN: Functional Kolmogorov-Arnold Network for Medical Image Enhancement and Segmentation
2025-09-16 20:13:48Maksim Penkin (Lomonosov Moscow State University), Andrey Krylov (Lomonosov Moscow State University)Abstract
Medical image enhancement and segmentation are critical yet challenging tasks in modern clinical practice, constrained by artifacts and complex anatomical variations. Traditional deep learning approaches often rely on complex architectures with limited interpretability. While Kolmogorov-Arnold networks offer interpretable solutions, their reliance on flattened feature representations fundamentally disrupts the intrinsic spatial structure of imaging data. To address this issue we propose a Functional Kolmogorov-Arnold Network (FunKAN) -- a novel interpretable neural framework, designed specifically for image processing, that formally generalizes the Kolmogorov-Arnold representation theorem onto functional spaces and learns inner functions using Fourier decomposition over the basis Hermite functions. We explore FunKAN on several medical image processing tasks, including Gibbs ringing suppression in magnetic resonance images, benchmarking on IXI dataset. We also propose U-FunKAN as state-of-the-art binary medical segmentation model with benchmarks on three medical datasets: BUSI (ultrasound images), GlaS (histological structures) and CVC-ClinicDB (colonoscopy videos), detecting breast cancer, glands and polyps, respectively. Experiments on those diverse datasets demonstrate that our approach outperforms other KAN-based backbones in both medical image enhancement (PSNR, TV) and segmentation (IoU, F1). Our work bridges the gap between theoretical function approximation and medical image analysis, offering a robust, interpretable solution for clinical applications.
Abstract (translated)
URL
https://arxiv.org/abs/2509.13508
PDF
-
Using KL-Divergence to Focus Frequency Information in Low-Light Image Enhancement
2025-09-16 13:40:06Yan Xingyang, Huang Xiaohong, Zhang Zhao, You Tian, Xu ZihengAbstract
In the Fourier domain, luminance information is primarily encoded in the amplitude spectrum, while spatial structures are captured in the phase components. The traditional Fourier Frequency information fitting employs pixel-wise loss functions, which tend to focus excessively on local information and may lead to global information loss. In this paper, we present LLFDisc, a U-shaped deep enhancement network that integrates cross-attention and gating mechanisms tailored for frequency-aware enhancement. We propose a novel distribution-aware loss that directly fits the Fourier-domain information and minimizes their divergence using a closed-form KL-Divergence objective. This enables the model to align Fourier-domain information more robustly than with conventional MSE-based losses. Furthermore, we enhance the perceptual loss based on VGG by embedding KL-Divergence on extracted deep features, enabling better structural fidelity. Extensive experiments across multiple benchmarks demonstrate that LLFDisc achieves state-of-the-art performance in both qualitative and quantitative evaluations. Our code will be released at: this https URL
Abstract (translated)
在傅里叶域中，亮度信息主要编码在振幅谱中，而空间结构则捕获于相位组件中。传统的傅里叶频率信息拟合采用像素级损失函数，这种做法往往会过度关注局部信息，并可能导致全局信息的丢失。本文介绍了 LLFDisc，这是一个 U 形深度增强网络，集成了专为频域感知增强设计的交叉注意力和门控机制。我们提出了一种新颖的基于分布感知的损失方法，该方法直接拟合傅里叶域的信息并使用闭式 KL 散度目标函数最小化它们之间的差异。这使得模型能够比传统的基于 MSE 的损失更稳健地对齐傅里叶域信息。此外，我们在 VGG 基础上改进了感知损失，并通过在提取的深度特征中嵌入 KL 散度来增强结构保真度。广泛的跨多个基准测试的实验表明，LLFDisc 在定性和定量评估中均达到了最先进的性能。我们的代码将在以下链接发布：this https URL
URL
https://arxiv.org/abs/2509.13083
PDF
-
VRAE: Vertical Residual Autoencoder for License Plate Denoising and Deblurring
2025-09-10 08:35:21Cuong Nguyen, Dung T. Tran, Hong Nguyen, Xuan-Vu Phan, Nam-Phong NguyenAbstract
In real-world traffic surveillance, vehicle images captured under adverse weather, poor lighting, or high-speed motion often suffer from severe noise and blur. Such degradations significantly reduce the accuracy of license plate recognition systems, especially when the plate occupies only a small region within the full vehicle image. Restoring these degraded images a fast realtime manner is thus a crucial pre-processing step to enhance recognition performance. In this work, we propose a Vertical Residual Autoencoder (VRAE) architecture designed for the image enhancement task in traffic surveillance. The method incorporates an enhancement strategy that employs an auxiliary block, which injects input-aware features at each encoding stage to guide the representation learning process, enabling better general information preservation throughout the network compared to conventional autoencoders. Experiments on a vehicle image dataset with visible license plates demonstrate that our method consistently outperforms Autoencoder (AE), Generative Adversarial Network (GAN), and Flow-Based (FB) approaches. Compared with AE at the same depth, it improves PSNR by about 20\%, reduces NMSE by around 50\%, and enhances SSIM by 1\%, while requiring only a marginal increase of roughly 1\% in parameters.
Abstract (translated)
在实际的交通监控中，恶劣天气、照明条件差或高速移动拍摄的车辆图像常常会受到严重的噪点和模糊影响。这些退化显著降低了车牌识别系统的准确性，尤其是在车牌仅占据整个车辆图像很小一部分的情况下。因此，在实时情况下恢复这些受损的图像是一个关键的预处理步骤，以提高识别性能。在本研究中，我们提出了一种垂直残差自编码器（VRAE）架构，专门用于交通监控中的图像增强任务。该方法采用了一种增强策略，利用辅助模块在每个编码阶段注入输入感知特征来指导表示学习过程，从而在整个网络中更好地保持一般信息的完整性和质量，相比传统自编码器具有优势。 实验在一个包含可见车牌的车辆图像数据集上进行，结果表明我们的方法在性能上持续优于自编码器（AE）、生成对抗网络（GAN）和基于流的方法（FB）。与相同深度的自编码器相比，它将PSNR提高了约20%，降低了NMSE约50%，并提升了SSIM 1%，而仅需增加大约1%的参数量。
URL
https://arxiv.org/abs/2509.08392
PDF
-
Physics-Guided Rectified Flow for Low-light RAW Image Enhancement
Abstract
Enhancing RAW images captured under low light conditions is a challenging task. Recent deep learning based RAW enhancement methods have shifted from using real paired data to relying on synthetic datasets. These synthetic datasets are typically generated by physically modeling sensor noise, but existing approaches often consider only additive noise, ignore multiplicative components, and rely on global calibration that overlooks pixel level manufacturing variations. As a result, such methods struggle to accurately reproduce real sensor noise. To address these limitations, this paper derives a noise model from the physical noise generation mechanisms that occur under low illumination and proposes a novel composite model that integrates both additive and multiplicative noise. To solve the model, we introduce a physics based per pixel noise simulation and calibration scheme that estimates and synthesizes noise for each individual pixel, thereby overcoming the restrictions of traditional global calibration and capturing spatial noise variations induced by microscopic CMOS manufacturing differences. Motivated by the strong performance of rectified flow methods in image generation and processing, we further combine the physics-based noise synthesis with a rectified flow generative framework and present PGRF a physics-guided rectified flow framework for low light image enhancement. PGRF leverages the ability of rectified flows to model complex data distributions and uses physical guidance to steer the generation toward the desired clean image. To validate the effectiveness of the proposed model, we established the LLID dataset, an indoor low light benchmark captured with the Sony A7S II camera. Experimental results demonstrate that the proposed framework achieves significant improvements in low light RAW image enhancement.
Abstract (translated)
在低光条件下增强RAW图像是一项挑战性的任务。近期基于深度学习的RAW图像增强方法已从使用真实的配对数据转向依赖于合成数据集。这些合成数据集通常是通过物理建模传感器噪声来生成的，但现有的方法往往只考虑加性噪声，忽略乘法成分，并且依赖全局校准而忽略了像素级别的制造差异。因此，这样的方法难以准确再现实际传感器噪声。 为了解决这些问题，本文从低光照条件下的噪声生成机制出发推导出了一种新的噪声模型，并提出了一种集成了加性和乘法噪声的复合模型。为了求解该模型，我们引入了一个基于物理原理的逐像素噪声模拟和校准方案，它能够估计并合成每个单独像素的噪声，从而克服了传统全局校准的限制，并捕捉到由微小CMOS制造差异引起的空间噪声变化。 受到矫正流方法在图像生成和处理中表现出的强大性能的启发，我们将基于物理原理的噪声合成与一个矫正流生成框架相结合，并提出了PGRF（物理引导矫正流框架），用于低光图像增强。PGRF利用了矫正流建模复杂数据分布的能力，并采用物理指导使生成过程朝着所需的清晰图像方向发展。 为了验证所提出模型的有效性，我们建立了LLID数据集，这是一个使用索尼A7S II相机拍摄的室内低光照基准测试集。实验结果表明，所提出的框架在低光RAW图像增强方面取得了显著改进。
URL
https://arxiv.org/abs/2509.08330
PDF
-
CARDIE: clustering algorithm on relevant descriptors for image enhancement
2025-09-07 15:55:55Giulia Bonino, Luca Alberto RizzoAbstract
Automatic image clustering is a cornerstone of computer vision, yet its application to image enhancement remains limited, primarily due to the difficulty of defining clusters that are meaningful for this specific task. To address this issue, we introduce CARDIE, an unsupervised algorithm that clusters images based on their color and luminosity content. In addition, we introduce a method to quantify the impact of image enhancement algorithms on luminance distribution and local variance. Using this method, we demonstrate that CARDIE produces clusters more relevant to image enhancement than those derived from semantic image attributes. Furthermore, we demonstrate that CARDIE clusters can be leveraged to resample image enhancement datasets, leading to improved performance for tone mapping and denoising algorithms. To encourage adoption and ensure reproducibility, we publicly release CARDIE code on our GitHub.
Abstract (translated)
自动图像聚类是计算机视觉的基础，但将其应用于图像增强方面仍较为有限，主要原因是难以定义对这一特定任务有意义的聚类。为了解决这个问题，我们引入了CARDIE，这是一种无监督算法，根据图像的颜色和亮度内容进行聚类。此外，我们还提出了一种方法来量化图像增强算法对亮度分布和局部方差的影响。利用这种方法，我们展示了CARDIE产生的聚类比基于语义图像属性的聚类更相关于图像增强任务。进一步地，我们证明了CARDIE生成的聚类可以用来重新采样图像增强数据集，从而提高色调映射和去噪算法的表现。 为了鼓励采用并确保可重复性，我们在GitHub上公开发布了CARDIE代码。
URL
https://arxiv.org/abs/2509.06116
PDF
-
Dual Interaction Network with Cross-Image Attention for Medical Image Segmentation
2025-09-07 07:25:59Jeonghyun Noh, Wangsu Jeon, Jinsun ParkAbstract
Medical image segmentation is a crucial method for assisting professionals in diagnosing various diseases through medical imaging. However, various factors such as noise, blurriness, and low contrast often hinder the accurate diagnosis of diseases. While numerous image enhancement techniques can mitigate these issues, they may also alter crucial information needed for accurate diagnosis in the original image. Conventional image fusion strategies, such as feature concatenation can address this challenge. However, they struggle to fully leverage the advantages of both original and enhanced images while suppressing the side effects of the enhancements. To overcome the problem, we propose a dual interactive fusion module (DIFM) that effectively exploits mutual complementary information from the original and enhanced images. DIFM employs cross-attention bidirectionally to simultaneously attend to corresponding spatial information across different images, subsequently refining the complementary features via global spatial attention. This interaction leverages low- to high-level features implicitly associated with diverse structural attributes like edges, blobs, and object shapes, resulting in enhanced features that embody important spatial characteristics. In addition, we introduce a multi-scale boundary loss based on gradient extraction to improve segmentation accuracy at object boundaries. Experimental results on the ACDC and Synapse datasets demonstrate the superiority of the proposed method quantitatively and qualitatively. Code available at: this https URL
Abstract (translated)
医学图像分割是通过医学成像帮助专业人士诊断各种疾病的重要方法。然而，诸如噪声、模糊和低对比度等因素往往阻碍了疾病的准确诊断。尽管有许多图像增强技术可以缓解这些问题，但它们可能会改变原始图像中进行准确诊断所需的关键信息。传统的图像融合策略（如特征级联）可以应对这一挑战，但在充分利用原始图像和增强图像的优势的同时抑制增强所带来的副作用方面存在困难。 为了解决这个问题，我们提出了一种双互动融合模块(Dual Interactive Fusion Module, DIFM)，该模块有效地利用了原始图像和增强图像之间的相互补充信息。DIFM采用双向交叉注意力机制，在不同图像之间同时关注相应的空间信息，并通过全局空间注意进一步精炼互补特征。这种交互作用隐含地关联了低到高级别的特征与边缘、斑点和物体形状等多样结构属性，从而产生了包含重要空间特征的增强特征。 此外，我们还引入了一种基于梯度提取的多尺度边界损失方法，以提高在对象边界处的分割准确性。 在ACDC（自动心脏诊断挑战赛）和Synapse数据集上的实验结果表明，所提出的方法在定量和定性方面都优于现有技术。代码可在以下网址获取：[此链接](https://this-url.com)（请将“this https URL”替换为实际提供的具体URL地址）。
URL
https://arxiv.org/abs/2509.05953
PDF
-
Unsupervised Ultra-High-Resolution UAV Low-Light Image Enhancement: A Benchmark, Metric and Framework
2025-09-01 11:20:07Wei Lu, Lingyu Zhu, Si-Bao ChenAbstract
Low light conditions significantly degrade Unmanned Aerial Vehicles (UAVs) performance in critical applications. Existing Low-light Image Enhancement (LIE) methods struggle with the unique challenges of aerial imagery, including Ultra-High Resolution (UHR), lack of paired data, severe non-uniform illumination, and deployment constraints. To address these issues, we propose three key contributions. First, we present U3D, the first unsupervised UHR UAV dataset for LIE, with a unified evaluation toolkit. Second, we introduce the Edge Efficiency Index (EEI), a novel metric balancing perceptual quality with key deployment factors: speed, resolution, model complexity, and memory footprint. Third, we develop U3LIE, an efficient framework with two training-only designs-Adaptive Pre-enhancement Augmentation (APA) for input normalization and a Luminance Interval Loss (L_int) for exposure control. U3LIE achieves SOTA results, processing 4K images at 23.8 FPS on a single GPU, making it ideal for real-time on-board deployment. In summary, these contributions provide a holistic solution (dataset, metric, and method) for advancing robust 24/7 UAV vision. The code and datasets are available at this https URL.
Abstract (translated)
在低光条件下，无人驾驶航空器（UAV）的性能会显著下降，特别是在关键应用中。现有的低光图像增强（LIE）方法难以应对航拍图像特有的挑战，包括超高分辨率（UHR）、缺乏配对数据、严重的非均匀照明以及部署限制等问题。为了应对这些问题，我们提出了三项主要贡献： 第一项是推出了U3D，这是首个用于LIE的无监督超高分辨率无人机数据集，并附带统一评估工具包。 第二项是引入了边缘效率指数（EEI），这是一种新颖的指标，在感知质量与关键部署因素（速度、分辨率、模型复杂度和内存占用）之间实现了平衡。 第三项是我们开发了一个高效的框架U3LIE，该框架包含两项训练专用设计：自适应预增强数据扩充（APA），用于输入标准化；以及亮度区间损失（L_int），用于曝光控制。U3LIE在处理4K图像方面达到了最先进的水平，在单个GPU上可以实现每秒23.8帧的速度，使其非常适合实时机载部署。 综上所述，这些贡献提供了一个全面的解决方案（数据集、指标和方法）来推进全天候无人机视觉技术的发展。代码和数据集可以在提供的链接中获取。
URL
https://arxiv.org/abs/2509.01373
PDF
-
Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement
2025-09-01 11:03:13Jiayi Gao, Changcheng Hua, Qingchao Chen, Yuxin Peng, Yang LiuAbstract
Identity-preserving text-to-video (IPT2V) generation creates videos faithful to both a reference subject image and a text prompt. While fine-tuning large pretrained video diffusion models on ID-matched data achieves state-of-the-art results on IPT2V, data scarcity and high tuning costs hinder broader improvement. We thus introduce a Training-Free Prompt, Image, and Guidance Enhancement (TPIGE) framework that bridges the semantic gap between the video description and the reference image and design sampling guidance that enhances identity preservation and video quality, achieving performance gains at minimal this http URL, we first propose Face Aware Prompt Enhancement, using GPT-4o to enhance the text prompt with facial details derived from the reference image. We then propose Prompt Aware Reference Image Enhancement, leveraging an identity-preserving image generator to refine the reference image, rectifying conflicts with the text prompt. The above mutual refinement significantly improves input quality before video generation. Finally, we propose ID-Aware Spatiotemporal Guidance Enhancement, utilizing unified gradients to optimize identity preservation and video quality jointly during this http URL method outperforms prior work and is validated by automatic and human evaluations on a 1000 video test set, winning first place in the ACM Multimedia 2025 Identity-Preserving Video Generation Challenge, demonstrating state-of-the-art performance and strong generality. The code is available at this https URL.
Abstract (translated)
身份保持型文本到视频（IPT2V）生成旨在创建既忠实于参考主体图像又符合文本提示的视频。尽管通过在匹配ID的数据上微调大规模预训练的视频扩散模型可以实现当前最先进的IPT2V性能，但数据稀缺和高昂的调整成本限制了进一步改进的可能性。因此，我们引入了一个无需训练的提示、图像和引导增强（TPIGE）框架，该框架弥合了视频描述与参考图像之间的语义差距，并设计了一种采样指导方法以提升身份保持性和视频质量，在最少的计算资源需求下实现了性能提升。 首先，我们提出了面部感知型提示增强，利用GPT-4o从参考图像中提取面部细节来优化文本提示。接着，我们提出了提示感知型参考图像增强，通过使用一种保真度高的图像生成器精炼参考图像，从而解决与文本提示之间的冲突。上述互惠改进在视频生成前显著提升了输入质量。最后，我们提出了身份感知时空引导增强，利用统一的梯度优化身份保持和视频质量。 这种方法不仅超越了以往的工作，并通过自动评估和人类评价在一个包含1000个视频的数据集上得到了验证，在ACM多媒体2025年身份保持型视频生成挑战赛中获得第一名，展示了其领先性能和广泛适用性。相关代码可在该链接获取。
URL
https://arxiv.org/abs/2509.01362
PDF
-
DRetNet: A Novel Deep Learning Framework for Diabetic Retinopathy Diagnosis
2025-09-01 02:27:16Idowu Paul Okuwobi, Jingyuan Liu, Jifeng Wan, Jiaojiao JiangAbstract
Diabetic retinopathy (DR) is a leading cause of blindness worldwide, necessitating early detection to prevent vision loss. Current automated DR detection systems often struggle with poor-quality images, lack interpretability, and insufficient integration of domain-specific knowledge. To address these challenges, we introduce a novel framework that integrates three innovative contributions: (1) Adaptive Retinal Image Enhancement Using Physics-Informed Neural Networks (PINNs): this technique dynamically enhances retinal images by incorporating physical constraints, improving the visibility of critical features such as microaneurysms, hemorrhages, and exudates; (2) Hybrid Feature Fusion Network (HFFN): by combining deep learning embeddings with handcrafted features, HFFN leverages both learned representations and domain-specific knowledge to enhance generalization and accuracy; (3) Multi-Stage Classifier with Uncertainty Quantification: this method breaks down the classification process into logical stages, providing interpretable predictions and confidence scores, thereby improving clinical trust. The proposed framework achieves an accuracy of 92.7%, a precision of 92.5%, a recall of 92.6%, an F1-score of 92.5%, an AUC of 97.8%, a mAP of 0.96, and an MCC of 0.85. Ophthalmologists rated the framework's predictions as highly clinically relevant (4.8/5), highlighting its alignment with real-world diagnostic needs. Qualitative analyses, including Grad-CAM visualizations and uncertainty heatmaps, further enhance the interpretability and trustworthiness of the system. The framework demonstrates robust performance across diverse conditions, including low-quality images, noisy data, and unseen datasets. These features make the proposed framework a promising tool for clinical adoption, enabling more accurate and reliable DR detection in resource-limited settings.
Abstract (translated)
糖尿病视网膜病变（DR）是全球导致失明的主要原因之一，因此早期检测以防止视力丧失至关重要。目前的自动化DR检测系统在处理质量较差的图像时往往表现不佳，并且缺乏可解释性以及特定领域的知识整合不足。为了应对这些挑战，我们提出了一种新颖的框架，集成了三个创新贡献： 1. **基于物理信息神经网络（PINNs）的自适应视网膜图像增强**：该技术通过引入物理约束动态地增强了视网膜图像，提高了微动脉瘤、出血和渗出等关键特征的可见性。 2. **混合特征融合网络（HFFN）**：通过结合深度学习嵌入与手工设计的特征，HFFN 利用已学得的表示以及特定领域的知识来提升泛化能力和准确性。 3. **多阶段分类器及不确定性量化**：此方法将分类过程分解为逻辑步骤，提供可解释的预测和置信度评分，从而增强临床信任。 所提出的框架达到了92.7%的准确率、92.5%的精确率、92.6%的召回率、92.5%的F1分数、97.8%的AUC值、0.96的mAP和0.85的MCC。眼科医生将该框架的预测评为高度临床相关（4.8/5分），突显了它与实际诊断需求的高度一致。通过Grad-CAM可视化分析以及不确定性热图等定性分析，进一步增强了系统的可解释性和可信度。 此框架在各种条件下表现出色，包括质量较差的图像、噪音数据和未见过的数据集。这些特性使得所提出的框架成为临床应用中的有力工具，在资源有限的情况下实现更准确且可靠的DR检测。
URL
https://arxiv.org/abs/2509.01072
PDF
-
A Unified Low-level Foundation Model for Enhancing Pathology Image Quality
2025-09-01 02:24:34Ziyi Liu, Zhe Xu, Jiabo Ma, Wenqaing Li, Junlin Hou, Fuxiang Huang, Xi Wang, Ronald Cheong Kin Chan, Terence Tsz Wai Wong, Hao ChenAbstract
Foundation models have revolutionized computational pathology by achieving remarkable success in high-level diagnostic tasks, yet the critical challenge of low-level image enhancement remains largely unaddressed. Real-world pathology images frequently suffer from degradations such as noise, blur, and low resolution due to slide preparation artifacts, staining variability, and imaging constraints, while the reliance on physical staining introduces significant costs, delays, and inconsistency. Although existing methods target individual problems like denoising or super-resolution, their task-specific designs lack the versatility to handle the diverse low-level vision challenges encountered in practice. To bridge this gap, we propose the first unified Low-level Pathology Foundation Model (LPFM), capable of enhancing image quality in restoration tasks, including super-resolution, deblurring, and denoising, as well as facilitating image translation tasks like virtual staining (H&E and special stains), all through a single adaptable architecture. Our approach introduces a contrastive pre-trained encoder that learns transferable, stain-invariant feature representations from 190 million unlabeled pathology images, enabling robust identification of degradation patterns. A unified conditional diffusion process dynamically adapts to specific tasks via textual prompts, ensuring precise control over output quality. Trained on a curated dataset of 87,810 whole slied images (WSIs) across 34 tissue types and 5 staining protocols, LPFM demonstrates statistically significant improvements (p<0.01) over state-of-the-art methods in most tasks (56/66), achieving Peak Signal-to-Noise Ratio (PSNR) gains of 10-15% for image restoration and Structural Similarity Index Measure (SSIM) improvements of 12-18% for virtual staining.
Abstract (translated)
基础模型在计算病理学中取得了重大突破，通过在高级诊断任务中的卓越成功实现了这一目标，然而低级图像增强的关键挑战仍未得到充分解决。实际的病理图像常常因载玻片制备缺陷、染色变异和成像限制而遭受噪声、模糊和分辨率降低等退化问题，依赖于物理染色又引入了显著的成本、延迟以及不一致性。尽管现有的方法针对诸如去噪或超分辨率这样的个别问题，但它们的任务特定设计缺乏处理实践中遇到的各种低级视觉挑战的灵活性。为弥合这一差距，我们提出了首个统一的低级病理基础模型（LPFM），该模型能够在包括超分辨率、去模糊和去噪在内的图像恢复任务中提升图像质量，并通过单个可适应架构促进诸如虚拟染色（H&E及特殊染料）等图像转换任务。我们的方法引入了一个对比预训练编码器，它从1.9亿张未标记的病理图像中学习到可以转移且不受染色影响的功能表示，从而能够稳健地识别退化模式。一个统一的条件扩散过程通过文本提示动态适应特定任务，确保精确控制输出质量。LPFM在87,810张全切片图像（WSIs）组成的精心策划的数据集上进行训练，这些图像是34种组织类型和5种染色协议的一部分，并且在大多数任务中（共66项中的56项），表现出统计显著性改进（p<0.01），实现了图像恢复的峰值信噪比（PSNR）提高10-15%，以及虚拟染色的结构相似度指数测量（SSIM）改善了12-18%。
URL
https://arxiv.org/abs/2509.01071
PDF
-
Efficient and Privacy-Protecting Background Removal for 2D Video Streaming using iPhone 15 Pro Max LiDAR
2025-08-27 20:14:12Jessica Kinnevan, Naifa Alqahtani, Toral ChauhanAbstract
Light Detection and Ranging (LiDAR) technology in consumer-grade mobile devices can be used as a replacement for traditional background removal and compositing techniques. Unlike approaches such as chroma keying and trained AI models, LiDAR's depth information is independent of subject lighting, and performs equally well in low-light and well-lit environments. We integrate the LiDAR and color cameras on the iPhone 15 Pro Max with GPU-based image processing. We use Apple's SwiftUI and Swift frameworks for user interface and backend development, and Metal Shader Language (MSL) for realtime image enhancement at the standard iPhone streaming frame rate of 60 frames per second. The only meaningful limitations of the technology are the streaming bandwidth of the depth data, which currently reduces the depth map resolution to 320x240, and any pre-existing limitations of the LiDAR IR laser to reflect accurate depth from some materials. If the LiDAR resolution on a mobile device like the iPhone can be improved to match the color image resolution, LiDAR could feasibly become the preeminent method of background removal for video applications and photography.
Abstract (translated)
光探测与测距（LiDAR）技术在消费级移动设备中的应用可以作为传统背景移除和合成技术的替代方案。与传统的色键技术和训练有素的人工智能模型相比，LiDAR提供的深度信息不受物体照明条件的影响，在低光和强光环境下表现同样出色。我们将在iPhone 15 Pro Max上集成LiDAR和彩色相机，并结合基于GPU的图像处理技术进行开发。 我们使用Apple的SwiftUI和Swift框架来构建用户界面和后端功能，同时采用Metal Shader Language（MSL）实现实时图像增强，以达到标准的iPhone流媒体帧率60帧每秒。目前这项技术的主要限制在于深度数据的传输带宽，这导致当前的深度图分辨率只能达到320x240像素，并且某些材料对LiDAR红外激光反射不准确的问题也会影响性能。 如果未来移动设备如iPhone上的LiDAR分辨率能够提升至与彩色图像相同的分辨率水平，那么LiDAR技术有望成为视频应用和摄影中背景移除的首选方法。
URL
https://arxiv.org/abs/2508.20250
PDF
-
A Frequency-Aware Self-Supervised Learning for Ultra-Wide-Field Image Enhancement
2025-08-27 08:24:20Weicheng Liao, Zan Chen, Jianyang Xie, Yalin Zheng, Yuhui Ma, Yitian ZhaoAbstract
Ultra-Wide-Field (UWF) retinal imaging has revolutionized retinal diagnostics by providing a comprehensive view of the retina. However, it often suffers from quality-degrading factors such as blurring and uneven illumination, which obscure fine details and mask pathological information. While numerous retinal image enhancement methods have been proposed for other fundus imageries, they often fail to address the unique requirements in UWF, particularly the need to preserve pathological details. In this paper, we propose a novel frequency-aware self-supervised learning method for UWF image enhancement. It incorporates frequency-decoupled image deblurring and Retinex-guided illumination compensation modules. An asymmetric channel integration operation is introduced in the former module, so as to combine global and local views by leveraging high- and low-frequency information, ensuring the preservation of fine and broader structural details. In addition, a color preservation unit is proposed in the latter Retinex-based module, to provide multi-scale spatial and frequency information, enabling accurate illumination estimation and correction. Experimental results demonstrate that the proposed work not only enhances visualization quality but also improves disease diagnosis performance by restoring and correcting fine local details and uneven intensity. To the best of our knowledge, this work is the first attempt for UWF image enhancement, offering a robust and clinically valuable tool for improving retinal disease management.
Abstract (translated)
超宽视野(UWF)视网膜成像技术通过提供视网膜的全面视角，彻底革新了视网膜诊断。然而，这种技术经常受到诸如模糊和不均匀照明等质量下降因素的影响，这些因素掩盖了细节并隐藏了病理信息。虽然已经提出了许多针对其他眼底影像图像增强的方法，但它们往往未能解决UWF成像的独特需求，尤其是保持病理细节的需求。在本文中，我们提出了一种新颖的频率感知自监督学习方法，专门用于UWF图像增强。该方法包含了频域解耦图像去模糊和基于Retinex引导的光照补偿模块。在一个模块中引入了不对称通道集成操作，以便利用高频和低频信息来结合全局视图与局部视图，确保精细结构和更广泛结构细节的保留。另外，在第二个基于Retinex的方法模块中提出了色彩保持单元，该单元提供了多尺度的空间和频率信息，从而实现了精确的光照估计和校正。实验结果表明，所提出的方法不仅提高了可视化质量，还通过恢复并修正局部细节点和不均匀强度而改善了疾病的诊断性能。据我们所知，这是首次尝试针对UWF图像增强进行的工作，并为提高视网膜疾病管理提供了一种稳健且具有临床价值的工具。
URL
https://arxiv.org/abs/2508.19664
PDF
