DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models
University of Ljubljana, Faculty of Electrical Engineering（卢布尔雅那大学电气工程学院）；University of Ljubljana, Faculty of Computer and Information Science（卢布尔雅那大学计算机与信息科学学院）
Modern face recognition (FR) models excel in constrained scenarios, but often suffer from decreased performance when deployed in unconstrained (real-world) environments due to uncertainties surrounding the quality of the captured facial data. Face image quality assessment (FIQA) techniques aim to mitigate these performance degradations by providing FR models with sample-quality predictions that can be used to reject low-quality samples and reduce false match errors. However, despite steady improvements, ensuring reliable quality estimates across facial images with diverse characteristics remains challenging. In this paper, we present a powerful new FIQA approach, named DifFIQA, which relies on denoising diffusion probabilistic models (DDPM) and ensures highly competitive results. The main idea behind the approach is to utilize the forward and backward processes of DDPMs to perturb facial images and quantify the impact of these perturbations on the corresponding image embeddings for quality prediction. Because the diffusion-based perturbations are computationally expensive, we also distill the knowledge encoded in DifFIQA into a regression-based quality predictor, called DifFIQA(R), that balances performance and execution time. We evaluate both models in comprehensive experiments on 7 datasets, with 4 target FR models and against 10 state-of-the-art FIQA techniques with highly encouraging results. The source code will be made publicly available.
A wide variety of image denoising methods are available now. However, the performance of a denoising algorithm often depends on individual input noisy images as well as its parameter setting. In this paper, we present a no-reference image denoising quality assessment method that can be used to select for an input noisy image the right denoising algorithm with the optimal parameter setting. This is a challenging task as no ground truth is available. This paper presents a data-driven approach to learn to predict image denoising quality. Our method is based on the observation that while individua…
In this paper we propose a measure of anisotropy as a quality parameter to estimate the amount of noise in noisy images. The anisotropy of an image can be determined through a directional measure, using an appropriate statistical distribution of the information contained in the image. This new measure is achieved through a stack filtering paradigm. First, we define a local directional entropy, based on the distribution of 0's and 1's in the neigborhood of every pixel location of each stack level. Then the entropy variation of this directional entropy is used to define an anisotropic measure. T…
Tampere University of Technology（坦佩雷理工大学）；National Aerospace University（国立航空航天大学）
This paper studies the problem of full reference visual quality assessment of denoised images with a special emphasis on images with low contrast and noise-like texture. Denoising of such images together with noise removal often results in image details loss or smoothing. A new test image database, FLT, containing 75 noise-free "reference" images and 300 filtered ("distorted") images is developed. Each reference image, corrupted by an additive white Gaussian noise, is denoised by the BM3D filter with four different values of threshold parameter (four levels of noise suppression). After carryin…
Feature Denoising Diffusion Model for Blind Image Quality Assessment
Key Laboratory of Multimedia Trusted Perception and Efficient Computing（多媒体可信感知与高效计算重点实验室）；Ministry of Education of China（中国教育部）；Xiamen University School of Medicine, Xiamen University（厦门大学医学院，厦门大学）；School of Information and Electronics, Beijing Institute of Technology（北京理工大学信息与电子学院）；Tencent Youtu Lab（腾讯优图实验室）；School of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）
A Deep-Learning-Based Label-free No-Reference Image Quality Assessment Metric: Application in Sodium MRI Denoising
University of Cambridge（剑桥大学）；Universitat de Barcelona（巴塞罗那大学）；Haukeland University Hospital（霍克兰大学医院）；University of York（约克大学）；Manchester Metropolitan University（曼彻斯特城市大学）
Rician Denoising Diffusion Probabilistic Models For Sodium Breast MRI Enhancement
University of Cambridge（剑桥大学）；Universitat de Barcelona（巴塞罗那大学）；Haukeland University Hospital（豪克兰大学医院）；University of York（约克大学）；Manchester Metropolitan University（曼彻斯特城市大学）
College of Computer Science, Sichuan University（四川大学计算机学院）；School of Engineering and Computer Science, Victoria University of Wellington（惠灵顿维多利亚大学工程与计算机科学学院）
Hyperspectral images (HSIs) are susceptible to various noise factors leading to the loss of information, and the noise restricts the subsequent HSIs object detection and classification tasks. In recent years, learning-based methods have demonstrated their superior strengths in denoising the HSIs. Unfortunately, most of the methods are manually designed based on the extensive expertise that is not necessarily available to the users interested. In this paper, we propose a novel algorithm to automatically build an optimal Convolutional Neural Network (CNN) to effectively denoise HSIs. Particularl…
Institute of Microelectronics, Tsinghua University（清华大学微电子学研究所）；Graduate School at Shenzhen, Tsinghua University（清华大学深圳国际研究生院）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）
The quality of images captured by wireless capsule endoscopy (WCE) is key for doctors to diagnose diseases of gastrointestinal (GI) tract. However, there exist many low-quality endoscopic images due to the limited illumination and complex environment in GI tract. After an enhancement process, the severe noise become an unacceptable problem. The noise varies with different cameras, GI tract environments and image enhancement. And the noise model is hard to be obtained. This paper proposes a convolutional blind denoising network for endoscopic images. We apply Deep Image Prior (DIP) method to re…
Universität Bremen（不来梅大学）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；Berlin Institute of Technology（柏林工业大学）
In most practical situations, the compression or transmission of images and videos creates distortions that will eventually be perceived by a human observer. Vice versa, image and video restoration techniques, such as inpainting or denoising, aim to enhance the quality of experience of human viewers. Correctly assessing the similarity between an image and an undistorted reference image as subjectively experienced by a human viewer can thus lead to significant improvements in any transmission, compression, or restoration system. This paper introduces the Haar wavelet-based perceptual similarity…
Tel-Aviv University（特拉维夫大学）；Technion – Israel Institute of Technology（以色列理工学院）
We present DeepISP, a full end-to-end deep neural model of the camera image signal processing (ISP) pipeline. Our model learns a mapping from the raw low-light mosaiced image to the final visually compelling image and encompasses low-level tasks such as demosaicing and denoising as well as higher-level tasks such as color correction and image adjustment. The training and evaluation of the pipeline were performed on a dedicated dataset containing pairs of low-light and well-lit images captured by a Samsung S7 smartphone camera in both raw and processed JPEG formats. The proposed solution achiev…
University of Bristol（布里斯托大学）；New York University（纽约大学）
The L1 norm regularized least squares method is often used for finding sparse approximate solutions and is widely used in 1-D signal restoration. Basis pursuit denoising (BPD) performs noise reduction in this way. However, the shortcoming of using L1 norm regularization is the underestimation of the true solution. Recently, a class of non-convex penalties have been proposed to improve this situation. This kind of penalty function is non-convex itself, but preserves the convexity property of the whole cost function. This approach has been confirmed to offer good performance in 1-D signal denois…
Philips Research（飞利浦研究院）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；Eindhoven University of Technology（埃因霍温理工大学）
Image quality assessment (IQA) algorithms aim to reproduce the human's perception of the image quality. The growing popularity of image enhancement, generation, and recovery models instigated the development of many methods to assess their performance. However, most IQA solutions are designed to predict image quality in the general domain, with the applicability to specific areas, such as medical imaging, remaining questionable. Moreover, the selection of these IQA metrics for a specific task typically involves intentionally induced distortions, such as manually added noise or artificial blurr…
A big part of the video content we consume from video providers consists of genres featuring low-light aesthetics. Low light sequences have special characteristics, such as spatio-temporal varying acquisition noise and light flickering, that make the encoding process challenging. To deal with the spatio-temporal incoherent noise, higher bitrates are used to achieve high objective quality. Additionally, the quality assessment metrics and methods have not been designed, trained or tested for this type of content. This has inspired us to trigger research in that area and propose a Grand Challenge…
City University of Hong Kong（香港城市大学）；Howard Hughes Medical Institute（霍华德·休斯医学研究所）；New York University（纽约大学）
The performance of objective image quality assessment (IQA) models has been evaluated primarily by comparing model predictions to human quality judgments. Perceptual datasets gathered for this purpose have provided useful benchmarks for improving IQA methods, but their heavy use creates a risk of overfitting. Here, we perform a large-scale comparison of IQA models in terms of their use as objectives for the optimization of image processing algorithms. Specifically, we use eleven full-reference IQA models to train deep neural networks for four low-level vision tasks: denoising, deblurring, supe…
AgentPolyp: Accurate Polyp Segmentation via Image Enhancement Agent
School of Mathematics, Shandong University（山东大学数学学院）；School of Information Science and Engineering, Shandong Normal University（山东师范大学信息科学与工程学院）；Yeshiva University（叶史瓦大学）；School of cyber science and technology, Sun Yat-sen University（中山大学网络空间安全学院）
Two-dimensional (2D) fast spin echo (FSE) techniques play a central role in the clinical magnetic resonance imaging (MRI) of knee joints. Moreover, three-dimensional (3D) FSE provides high-isotropic-resolution magnetic resonance (MR) images of knee joints, but it has a reduced signal-to-noise ratio compared to 2D FSE. Deep-learning denoising methods are a promising approach for denoising MR images, but they are often trained using synthetic noise due to challenges in obtaining true noise distributions for MR images. In this study, inherent true noise information from 2-NEX acquisition was used…
National Tsing Hua University（国立清华大学）；Florida International University（佛罗里达国际大学）；Lehigh University（理海大学）；Guangdong Provincial People’s Hospital（广东省人民医院）；Guangdong Academy of Medical Science（广东省医学科学院）；University of Notre Dame（圣母大学）
Deep learning had already demonstrated its power in medical images, including denoising, classification, segmentation, etc. All these applications are proposed to automatically analyze medical images beforehand, which brings more information to radiologists during clinical assessment for accuracy improvement. Recently, many medical denoising methods had shown their significant artifact reduction result and noise removal both quantitatively and qualitatively. However, those existing methods are developed around human-vision, i.e., they are designed to minimize the noise effect that can be perce…
Volumetric Conditional Score-based Residual Diffusion Model for PET/MR Denoising
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）；Neuroscience Research Institute（神经科学研究所）；Gachon University of Medicine and Science（嘉泉医科大学）
AnF-DiffPET: Anatomy- and Frequency-Guided Diffusion for PET/CT Denoising
College of Medicine and Biological Information Engineering, Northeastern University（东北大学医学与生物信息工程学院）；Tohoku University School of Medicine（东北大学医学院）；Department of Clinical Neurosciences, University of Cambridge（剑桥大学临床神经科学系）
Enhanced Confocal Laser Scanning Microscopy with Adaptive Physics Informed Deep Autoencoders
Georgia State University（佐治亚州立大学）；Riphah International University（里法国际大学）；Roots IVY（鲁茨艾维）；Arid Agriculture University（干旱农业大学）；University of Central Florida（中佛罗里达大学）
Computed tomography (CT) is a popular medical imaging modality in clinical applications. At the same time, the x-ray radiation dose associated with CT scans raises public concerns due to its potential risks to the patients. Over the past years, major efforts have been dedicated to the development of Low-Dose CT (LDCT) methods. However, the radiation dose reduction compromises the signal-to-noise ratio (SNR), leading to strong noise and artifacts that down-grade CT image quality. In this paper, we propose a novel 3D noise reduction method, called Structure-sensitive Multi-scale Generative Adver…
Washington University in St. Louis（圣路易斯华盛顿大学）；Mallinckrodt Institute of Radiology（马林克罗特放射学研究所）
Multiple objective assessment of image-quality-based studies have reported that several deep-learning-based denoising methods show limited performance on signal-detection tasks. Our goal was to investigate the reasons for this limited performance. To achieve this goal, we conducted a task-based characterization of a DL-based denoising approach for individual signal properties. We conducted this study in the context of evaluating a DL-based approach for denoising SPECT images. The training data consisted of signals of different sizes and shapes within a clustered-lumpy background, imaged with a…
Fine-Grained GRPO for Precise Preference Alignment in Flow Models
Shanghai Jiao Tong University（上海交通大学）；University of Science and Technology of China（中国科学技术大学）；Fudan University（复旦大学）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）
Automating Parameter Selection in Deep Image Prior for Fluorescence Microscopy Image Denoising via Similarity-Based Parameter Transfer
Institute for Applied Medical Informatics, Institute of Computational Neuroscience, Center for Biomedical Artificial Intelligence (bAIome), University Medical Center Hamburg-Eppendorf, Germany（应用医学信息学研究所、计算神经科学研究所、生物医学人工智能中心（bAIome）、汉堡-埃彭多夫大学医学中心，德国）；Institute for Biomedical Imaging, Hamburg University of Technology, Hamburg, Germany（生物医学成像研究所、汉堡技术大学、汉堡，德国）；Department of Biomedical Imaging, University Medical Center Hamburg-Eppendorf, Germany（生物医学成像系、汉堡-埃彭多夫大学医学中心，德国）；Fraunhofer Research Institution for Individualized Medical Technology（弗劳恩霍夫个性化医疗技术研究机构）；Institute of Medical Microbiology, Virology and Hygiene, University Medical Center Hamburg-Eppendorf, Germany（医学微生物学研究所、病毒学与卫生学、汉堡-埃彭多夫大学医学中心，德国）；Institute of Biochemistry and Molecular Cell Biology, University Medical Center Hamburg-Eppendorf, Germany（生物化学与分子细胞生物学研究所、汉堡-埃彭多夫大学医学中心，德国）
Objective and Interpretable Breast Cosmesis Evaluation with Attention Guided Denoising Diffusion Anomaly Detection Model
Yonsei College of Medicine（延世大学医学院）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；Yongin Severance Hospital（龙仁Severance医院）；Yonsei University College of Medicine（延世大学医学院）
Amsterdam UMC（阿姆斯特丹大学医学中心）；University of Amsterdam（阿姆斯特丹大学）；MS Center Amsterdam（阿姆斯特丹多发性硬化中心）；Amsterdam Neuroscience（阿姆斯特丹神经科学研究所）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Leiden University（莱顿大学）；Delft University of Technology（代尔夫特理工大学）
Machine Learning methods can learn how to reconstruct Magnetic Resonance Images and thereby accelerate acquisition, which is of paramount importance to the clinical workflow. Physics-informed networks incorporate the forward model of accelerated MRI reconstruction in the learning process. With increasing network complexity, robustness is not ensured when reconstructing data unseen during training. We aim to embed data consistency (DC) in deep networks while balancing the degree of network complexity. While doing so, we will assess whether either explicit or implicit enforcement of DC in varyin…
Diffusion Probe: Generated Image Result Prediction Using CNN Probes
Alibaba Group（阿里巴巴集团）；Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, School of Statistics and Data Science, Zhejiang Gongshang University（浙江工商大学统计与数据科学学院共同富裕统计监测与智能治理实验室）；Southeast University（东南大学）；College of Intelligent Robotics and Advanced Manufacturing, Fudan University（复旦大学智能机器人与先进制造学院）；ByteDance Inc.（字节跳动有限公司）
