Image Super-Resolution (SR) techniques improve visual quality by enhancing the spatial resolution of images. Quality evaluation metrics play a critical role in comparing and optimizing SR algorithms, but current metrics achieve only limited success, largely due to the lack of large-scale quality databases, which are essential for learning accurate and robust SR quality metrics. In this work, we first build a large-scale SR image database using a novel semi-automatic labeling approach, which allows us to label a large number of images with manageable human workload. The resulting SR Image quality database with Semi-Automatic Ratings (SISAR), so far the largest of SR-IQA database, contains 8,400 images of 100 natural scenes. We train an end-to-end Deep Image SR Quality (DISQ) model by employing two-stream Deep Neural Networks (DNNs) for feature extraction, followed by a feature fusion network for quality prediction. Experimental results demonstrate that the proposed method outperforms state-of-the-art metrics and achieves promising generalization performance in cross-database tests. The SISAR database and DISQ model will be made publicly available to facilitate reproducible research.
There has been a growing interest in developing image super-resolution (SR) algorithms that convert low-resolution (LR) to higher resolution images, but automatically evaluating the visual quality of super-resolved images remains a challenging problem. Here we look at the problem of SR image quality assessment (SR IQA) in a two-dimensional (2D) space of deterministic fidelity (DF) versus statistical fidelity (SF). This allows us to better understand the advantages and disadvantages of existing SR algorithms, which produce images at different clusters in the 2D space of (DF, SF). Specifically, …
University of Waterloo（滑铁卢大学）；University of Science and Technology of China（中国科学技术大学）
Single image super-resolution (SISR) algorithms reconstruct high-resolution (HR) images with their low-resolution (LR) counterparts. It is desirable to develop image quality assessment (IQA) methods that can not only evaluate and compare SISR algorithms, but also guide their future development. In this paper, we assess the quality of SISR generated images in a two-dimensional (2D) space of structural fidelity versus statistical naturalness. This allows us to observe the behaviors of different SISR algorithms as a tradeoff in the 2D space. Specifically, SISR methods are traditionally designed t…
To support the application scenarios where high-resolution (HR) images are urgently needed, various single image super-resolution (SISR) algorithms are developed. However, SISR is an ill-posed inverse problem, which may bring artifacts like texture shift, blur, etc. to the reconstructed images, thus it is necessary to evaluate the quality of super-resolution images (SRIs). Note that most existing image quality assessment (IQA) methods were developed for synthetically distorted images, which may not work for SRIs since their distortions are more diverse and complicated. Therefore, in this paper…
University of Konstanz（康斯坦茨大学）；Northwestern Polytechnical University（西北工业大学）
Scale-invariance is an open problem in many computer vision subfields. For example, object labels should remain constant across scales, yet model predictions diverge in many cases. This problem gets harder for tasks where the ground-truth labels change with the presentation scale. In image quality assessment (IQA), downsampling attenuates impairments, e.g., blurs or compression artifacts, which can positively affect the impression evoked in subjective studies. To accurately predict perceptual image quality, cross-resolution IQA methods must therefore account for resolution-dependent errors ind…
An average observer perceives the world in color instead of black and white. Moreover, the visual system focuses on structures and segments instead of individual pixels. Based on these observations, we propose a full reference objective image quality metric modeling visual system characteristics and chroma similarity in the perceptually uniform color domain (Lab). Laplacian of Gaussian features are obtained in the L channel to model the retinal ganglion cells in human visual system and color similarity is calculated over the a and b channels. In the proposed perceptual similarity index (PerSIM…
Space and Naval Warfare Systems Center Pacific（太平洋空间与海战系统中心）
Traditional metrics for evaluating the efficacy of image processing techniques do not lend themselves to understanding the capabilities and limitations of modern image processing methods - particularly those enabled by deep learning. When applying image processing in engineering solutions, a scientist or engineer has a need to justify their design decisions with clear metrics. By applying blind/referenceless image spatial quality (BRISQUE), Structural SIMilarity (SSIM) index scores, and Peak signal-to-noise ratio (PSNR) to images before and after image processing, we can quantify quality impro…
AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results
Lomonosov Moscow State University（莫斯科罗蒙诺索夫国立大学）；MSU Institute for Artificial Intelligence（莫斯科国立大学人工智能研究所）；University of Würzburg（维尔茨堡大学）；ByteDance（字节跳动）；Tencent（腾讯）；School of Computer Science and Cyber Engineering, Guangzhou University（广州大学计算机科学与网络工程学院）；Shanghai Jiao Tong University（上海交通大学）
Despite the growing popularity of video super-resolution (VSR), there is still no good way to assess the quality of the restored details in upscaled frames. Some SR methods may produce the wrong digit or an entirely different face. Whether a method's results are trustworthy depends on how well it restores truthful details. Image super-resolution can use natural distributions to produce a high-resolution image that is only somewhat similar to the real one. VSR enables exploration of additional information in neighboring frames to restore details from the original scene. The ERQA metric, which w…
Samsung R&D UK（三星英国研发中心）；Massachusetts Institute of Technology（麻省理工学院）
Omnidirectional images (ODIs), also known as 360-degree images, enable viewers to explore all directions of a given 360-degree scene from a fixed point. Designing an immersive imaging system with ODI is challenging as such systems require very large resolution coverage of the entire 360 viewing space to provide an enhanced quality of experience (QoE). Despite remarkable progress on single image super-resolution (SISR) methods with deep-learning techniques, no study for quality assessments of super-resolved ODIs exists to analyze the quality of such SISR techniques. This paper proposes an objec…
Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment
School of Mathematical Sciences, Beihang University（北京航空航天大学数学学院）；School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）；School of Biomedical Engineering, Shenzhen University（深圳大学生物医学工程学院）；CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China（中国科学技术大学地球空间信息处理与应用系统国家重点实验室）；School of Information Science and Engineering, Ningbo University（宁波大学信息科学与工程学院）；School of Artificial Intelligence, Dalian University of Technology（大连理工大学人工智能学院）
FLNet: Flood-Induced Agriculture Damage Assessment using Super Resolution of Satellite Images
Annam.AI CoE, MoE, Indian Institute of Technology Ropar, Punjab, India（Annam.AI联合研究所、教育部、印度理工学院罗帕尔分校）；Department of Mathematical Sciences, Rajiv Gandhi Institute of Petroleum Technology, Jais, UP, India（数学科学系、拉贾吉安石油技术学院）；Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India（计算机科学与工程系、印度理工学院罗帕尔分校）
Textural-Perceptual Joint Learning for No-Reference Super-Resolution Image Quality Assessment
School of Software, Dalian University of Technology（大连理工大学软件学院）；International School of Information Science and Engineering, Dalian University of Technology（大连理工大学国际信息与工程学院）
Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions. However, effectively evaluating the perceptual quality of SR images remains a challenging research problem. In this paper, we propose a no-reference/blind deep neural network-based SR image quality assessor (DeepSRQ). To learn more discriminative feature representations of various distorted SR images, the proposed DeepSRQ is a two-stream convolutional network including two subcomponents for distorted structure and texture SR images. …
Eurecat Centre Tecnològic（Eurecat技术中心）；Satellogic Inc（Satellogic公司）
Latest advances in Super-Resolution (SR) have been tested with general purpose images such as faces, landscapes and objects, mainly unused for the task of super-resolving Earth Observation (EO) images. In this research paper, we benchmark state-of-the-art SR algorithms for distinct EO datasets using both Full-Reference and No-Reference Image Quality Assessment (IQA) metrics. We also propose a novel Quality Metric Regression Network (QMRNet) that is able to predict quality (as a No-Reference metric) by training on any property of the image (i.e. its resolution, its distortions...) and also able…
The 4K content can deliver a more immersive visual experience to consumers due to the huge improvement of spatial resolution. However, existing blind image quality assessment (BIQA) methods are not suitable for the original and upscaled 4K contents due to the expanded resolution and specific distortions. In this paper, we propose a deep learning-based BIQA model for 4K content, which on one hand can recognize true and pseudo 4K content and on the other hand can evaluate their perceptual visual quality. Considering the characteristic that high spatial resolution can represent more abundant high…
Quality assessment for User Generated Content (UGC) videos plays an important role in ensuring the viewing experience of end-users. Previous UGC video quality assessment (VQA) studies either use the image recognition model or the image quality assessment (IQA) models to extract frame-level features of UGC videos for quality regression, which are regarded as the sub-optimal solutions because of the domain shifts between these tasks and the UGC VQA task. In this paper, we propose a very simple but effective UGC VQA model, which tries to address this problem by training an end-to-end spatial feat…
ENSTA Paris, Institut Polytechnique de Paris（巴黎高等先进技术学院，巴黎理工学院）；Safrantech, Safran Group（赛峰科技，赛峰集团）
Several metrics exist to quantify the similarity between images, but they are inefficient when it comes to measure the similarity of highly distorted images. In this work, we propose to empirically investigate perceptual metrics based on deep neural networks for tackling the Image Quality Assessment (IQA) task. We study deep perceptual metrics according to different hyperparameters like the network's architecture or training procedure. Finally, we propose our multi-resolution perceptual metric (MR-Perceptual), that allows us to aggregate perceptual information at different resolutions and outp…
In this work, we present an empirical study of DCGANs, including hyperparameter heuristics and image quality assessment, as a way to address the scarcity of datasets to investigate fetal head ultrasound. We present experiments to show the impact of different image resolutions, epochs, dataset size input, and learning rates for quality image assessment on four metrics: mutual information (MI), Fréchet inception distance (FID), peak-signal-to-noise ratio (PSNR), and local binary pattern vector (LBPv). The results show that FID and LBPv have stronger relationship with clinical image quality score…
Various and different methods can be used to produce high-resolution multispectral images from high-resolution panchromatic image (PAN) and low-resolution multispectral images (MS), mostly on the pixel level. However, the jury is still out on the benefits of a fused image compared to its original images. There is also a lack of measures for assessing the objective quality of the spatial resolution for the fusion methods. Therefore, an objective quality of the spatial resolution assessment for fusion images is required. So, this study attempts to develop a new qualitative assessment to evaluate…
MIT（麻省理工学院）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）
Fetal brain MRI is useful for diagnosing brain abnormalities but is challenged by fetal motion. The current protocol for T2-weighted fetal brain MRI is not robust to motion so image volumes are degraded by inter- and intra- slice motion artifacts. Besides, manual annotation for fetal MR image quality assessment are usually time-consuming. Therefore, in this work, a semi-supervised deep learning method that detects slices with artifacts during the brain volume scan is proposed. Our method is based on the mean teacher model, where we not only enforce consistency between student and teacher model…
City University of Hong Kong（香港城市大学）；Peng Cheng Laboratory（鹏城实验室）
Ensemble methods are generally regarded to be better than a single model if the base learners are deemed to be "accurate" and "diverse." Here we investigate a semi-supervised ensemble learning strategy to produce generalizable blind image quality assessment models. We train a multi-head convolutional network for quality prediction by maximizing the accuracy of the ensemble (as well as the base learners) on labeled data, and the disagreement (i.e., diversity) among them on unlabeled data, both implemented by the fidelity loss. We conduct extensive experiments to demonstrate the advantages of em…
NORCE Norwegian Research Centre（挪威研究中心）；Shenzhen University（深圳大学）
Transformer has become the new standard method in natural language processing (NLP), and it also attracts research interests in computer vision area. In this paper we investigate the application of Transformer in Image Quality (TRIQ) assessment. Following the original Transformer encoder employed in Vision Transformer (ViT), we propose an architecture of using a shallow Transformer encoder on the top of a feature map extracted by convolution neural networks (CNN). Adaptive positional embedding is employed in the Transformer encoder to handle images with arbitrary resolutions. Different setting…
City University of Hong Kong（香港城市大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
In real-world image enhancement, it is often challenging (if not impossible) to acquire ground-truth data, preventing the adoption of distance metrics for objective quality assessment. As a result, one often resorts to subjective quality assessment, the most straightforward and reliable means of evaluating image enhancement. Conventional subjective testing requires manually pre-selecting a small set of visual examples, which may suffer from three sources of biases: 1) sampling bias due to the extremely sparse distribution of the selected samples in the image space; 2) algorithmic bias due to p…
Xidian University（西安电子科技大学）；University of Southern California（南加州大学）
A new stereoscopic image quality assessment database rendered using the 2D-image-plus-depth source, called MCL-3D, is described and the performance benchmarking of several known 2D and 3D image quality metrics using the MCL-3D database is presented in this work. Nine image-plus-depth sources are first selected, and a depth image-based rendering (DIBR) technique is used to render stereoscopic image pairs. Distortions applied to either the texture image or the depth image before stereoscopic image rendering include: Gaussian blur, additive white noise, down-sampling blur, JPEG and JPEG-2000 (JP2…
School of Electronic Information, Wuhan University（武汉大学电子信息学院）
The goal in a blind image quality assessment (BIQA) model is to simulate the process of evaluating images by human eyes and accurately assess the quality of the image. Although many approaches effectively identify degradation, they do not fully consider the semantic content in images resulting in distortion. In order to fill this gap, we propose a deep adaptive superpixel-based network, namely DSN-IQA, to assess the quality of image based on multi-scale and superpixel segmentation. The DSN-IQA can adaptively accept arbitrary scale images as input images, making the assessment process similar t…
Purdue University Northwest（普渡大学西北校区）；University of Arkansas at Little Rock（阿肯色大学小石城分校）
Image quality is important, and can affect overall performance in image processing and computer vision as well as for numerous other reasons. Image quality assessment (IQA) is consequently a vital task in different applications from aerial photography interpretation to object detection to medical image analysis. In previous research, the BRISQUE algorithm and the PSNR algorithm were evaluated with high resolution (atleast 512x384 pixels), but relatively small image sets (no more than 4,744 images). However, scientists have not evaluated IQA algorithms on low resolution (no more than 32x32 pixe…
Ultra-High-Definition Image Quality Assessment via Graph Representation Learning
1 School of Information；Communication Engineering, Communication University of China, Beijing 100024, China 2 College of Engineering, Northeastern University, Silicon Valley, San Jose, CA 95113, USA 3 JancsiLab, JancsiTech, Hongkong 999077, China 4 Center of Information \& Network Technology, Beijing Normal University, Beijing 100875, China
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Korea University（高丽大学）
In this paper, we introduce an image quality assessment (IQA) method for pediatric T1- and T2-weighted MR images. IQA is first performed slice-wise using a nonlocal residual neural network (NR-Net) and then volume-wise by agglomerating the slice QA results using random forest. Our method requires only a small amount of quality-annotated images for training and is designed to be robust to annotation noise that might occur due to rater errors and the inevitable mix of good and bad slices in an image volume. Using a small set of quality-assessed images, we pre-train NR-Net to annotate each image …
Over the past decade, many Super Resolution techniques have been developed using deep learning. Among those, generative adversarial networks (GAN) and very deep convolutional networks (VDSR) have shown promising results in terms of HR image quality and computational speed. In this paper, we propose two approaches based on these two algorithms: VDSR-ResNeXt, which is a deep multi-branch convolutional network inspired by VDSR and ResNeXt; and SRCGAN, which is a conditional GAN that explicitly passes class labels as input to the GAN. The two methods were implemented on common SR benchmark dataset…
Jackson School of Geosciences（杰克逊地球科学学院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；CIRES, University of Colorado Boulder（科罗拉多大学博尔德分校环境科学研究合作研究所）；NOAA/Physical Sciences Laboratory（美国国家海洋和大气管理局物理科学实验室）；Purdue University（普渡大学）；Cockrell School of Engineering（科克雷尔工程学院）
Urban downscaling is a link to transfer the knowledge from coarser climate information to city scale assessments. These high-resolution assessments need multiyear climatology of past data and future projections, which are complex and computationally expensive to generate using traditional numerical weather prediction models. The city of Austin, Texas, USA has seen tremendous growth in the past decade. Systematic planning for the future requires the availability of fine resolution city-scale datasets. In this study, we demonstrate a novel approach generating a general purpose operator using dee…
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
University of Science and Technology of China（中国科学技术大学）；Hefei University of Technology（合肥工业大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）；Institute of Intelligent Machines, Chinese Academy of Sciences（中国科学院智能 Machines 研究所）
City University of Hong Kong（香港城市大学）；Kingsoft Cloud（金山云）
In this work, we propose a no-reference video quality assessment method, aiming to achieve high-generalization capability in cross-content, -resolution and -frame rate quality prediction. In particular, we evaluate the quality of a video by learning effective feature representations in spatial-temporal domain. In the spatial domain, to tackle the resolution and content variations, we impose the Gaussian distribution constraints on the quality features. The unified distribution can significantly reduce the domain gap between different video samples, resulting in a more generalized quality featu…
Multiclass Post-Earthquake Building Assessment Integrating High-Resolution Optical and SAR Satellite Imagery, Ground Motion, and Soil Data with Transformers
Department of Civil and Environmental Engineering, University of Houston, TX, USA（土木与环境工程系，德克萨斯大学）；Department of Electrical and Computer Engineering, University of Houston, TX, USA（电气与计算机工程系，德克萨斯大学）；Department of Earth and Atmospheric Science, University of Houston, TX, USA（地球与大气科学系，德克萨斯大学）；German Aerospace Center (DLR), Microwaves and Radar Institute, Munich, Germany（德国航天中心（DLR）微波与雷达研究所）
With the growing data consumption of emerging video applications and users requirement for higher resolutions, up to 8K, a huge effort has been made in video compression technologies. Recently, versatile video coding (VVC) has been standardized by the moving picture expert group (MPEG), providing a significant improvement in compression performance over its predecessor high efficiency video coding (HEVC). In this paper, we provide a comparative subjective quality evaluation between VVC and HEVC standards for 8K resolution videos. In addition, we evaluate the perceived quality improvement offer…
BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response
Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院）；RIKEN Center for Advanced Intelligence Project (AIP), RIKEN（日本理化学研究院先进智能项目中心）；Department of Photogrammetry and Remote Sensing, ETH Zürich（苏黎世联邦理工学院测绘与遥感系）；Microsoft Research Asia（微软亚洲研究院）
