Recently, image quality assessment (IQA) has achieved remarkable progress with the success of deep learning. However, the strict pre-condition of full-reference (FR) methods has limited its application in real scenarios. And the no-reference (NR) scheme is also inconvenient due to its unsatisfying performance as a result of ignoring the essence of image quality. In this paper, we introduce a brand new scheme, namely external-reference image quality assessment (ER-IQA), by introducing external reference images to bridge the gap between FR and NR-IQA. As the first implementation and a new baseline of ER-IQA, we propose a new Unpaired-IQA network to process images in a content-unpaired manner. A Mutual Attention-based Feature Enhancement (MAFE) module is well-designed for the unpaired features in ER-IQA. The MAFE module allows the network to extract quality-discriminative features from distorted images and content variability-robust features from external reference ones. Extensive experiments demonstrate that the proposed model outperforms the state-of-the-art NR-IQA methods, verifying the effectiveness of ER-IQA and the possibility of narrowing the gap of the two existing categories.
Shanghai Jiao Tong University（上海交通大学）；Peng Cheng Laboratory（鹏城实验室）；West Virginia University（西弗吉尼亚大学）；City University of Hong Kong（香港城市大学）
No-reference image quality assessment (NR-IQA) aims to quantify how humans perceive visual distortions of digital images without access to their undistorted references. NR-IQA models are extensively studied in computational vision, and are widely used for performance evaluation and perceptual optimization of man-made vision systems. Here we make one of the first attempts to examine the perceptual robustness of NR-IQA models. Under a Lagrangian formulation, we identify insightful connections of the proposed perceptual attack to previous beautiful ideas in computer vision and machine learning. W…
This paper reports on the NTIRE 2022 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2022. This challenge is held to address the emerging challenge of IQA by perceptual image processing algorithms. The output images of these algorithms have completely different characteristics from traditional distortions and are included in the PIPAL dataset used in this challenge. This challenge is divided into two tracks, a full-reference IQA track similar to the previous NTIRE IQA challeng…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；SenseTime Research（商汤科技研究院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) When focus on beating current benchmarks, are we getting better IR algorithms? …
The University of Sydney（悉尼大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent perceptual IR algorithms based on generative adversarial networks (GANs) have brought in significant improvement on visual performance, but also pose great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. We present two questions: Can existing IQA methods objectively evaluate recent IR algorithms? With the focus on beating current benchmarks, are we getting better IR algorith…
In this paper, we propose an image quality transformer (IQT) that successfully applies a transformer architecture to a perceptual full-reference image quality assessment (IQA) task. Perceptual representation becomes more important in image quality assessment. In this context, we extract the perceptual feature representations from each of input images using a convolutional neural network (CNN) backbone. The extracted feature maps are fed into the transformer encoder and decoder in order to compare a reference and distorted images. Following an approach of the transformer-based vision models, we…
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021. As a new type of image processing technology, perceptual image processing algorithms based on Generative Adversarial Networks (GAN) have produced images with more realistic textures. These output images have completely different characteristics from traditional distortions, thus pose a new challenge for IQA methods to evaluate their visual quality. In comparison with previous IQA challen…
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…
The quality of visual input is very important for both human and machine perception. Consequently many processing techniques exist that deal with different distortions. Usually image processing is applied freely and lacks redundancy regarding safety. We propose a novel image comparison method called the Combined Distances of Contrast Distributions (CD2) to protect against errors that arise during processing. Based on the distribution of image contrasts a new reduced-reference image quality assessment (IQA) method is introduced. By combining various distance functions excellent performance on I…
University of Würzburg（维尔茨堡大学）；Institute of Computer Science（计算机科学研究所）
Generative models for image restoration, enhancement, and generation have significantly improved the quality of the generated images. Surprisingly, these models produce more pleasant images to the human eye than other methods, yet, they may get a lower perceptual quality score using traditional perceptual quality metrics such as PSNR or SSIM. Therefore, it is necessary to develop a quantitative metric to reflect the performance of new algorithms, which should be well-aligned with the person's mean opinion score (MOS). Learning-based approaches for perceptual image quality assessment (IQA) usua…
Due to the strong correlation between visual attention and perceptual quality, many methods attempt to use human saliency information for image quality assessment. Although this mechanism can get good performance, the networks require human saliency labels, which is not easily accessible for omnidirectional images (ODI). To alleviate this issue, we propose a spatial attention-based perceptual quality prediction network for non-reference quality assessment on ODIs (SAP-net). To drive our SAP-net, we establish a large-scale IQA dataset of ODIs (IQA-ODI), which is composed of subjective scores of…
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…
City University of Hong Kong（香港城市大学）；Chongqing University（重庆大学）
Existing deep learning-based full-reference IQA (FR-IQA) models usually predict the image quality in a deterministic way by explicitly comparing the features, gauging how severely distorted an image is by how far the corresponding feature lies from the space of the reference images. Herein, we look at this problem from a different viewpoint and propose to model the quality degradation in perceptual space from a statistical distribution perspective. As such, the quality is measured based upon the Wasserstein distance in the deep feature domain. More specifically, the 1DWasserstein distance at e…
NORCE Norwegian Research Centre（NORCE挪威研究中心）；Hong Kong University of Science and Technology（香港科技大学）
Visual (image, video) quality assessments can be modelled by visual features in different domains, e.g., spatial, frequency, and temporal domains. Perceptual mechanisms in the human visual system (HVS) play a crucial role in generation of quality perception. This paper proposes a general framework for no-reference visual quality assessment using efficient windowed transformer architectures. A lightweight module for multi-stage channel attention is integrated into Swin (shifted window) Transformer. Such module can represent appropriate perceptual mechanisms in image quality assessment (IQA) to …
Image quality assessment (IQA) models aim to establish a quantitative relationship between visual images and their perceptual quality by human observers. IQA modeling plays a special bridging role between vision science and engineering practice, both as a test-bed for vision theories and computational biovision models, and as a powerful tool that could potentially make profound impact on a broad range of image processing, computer vision, and computer graphics applications, for design, optimization, and evaluation purposes. IQA research has enjoyed an accelerated growth in the past two decades…
Harbin Institute of Technology（哈尔滨工业大学）；Dalian Maritime University（大连海事大学）；Peng Cheng Laboratory（鹏城实验室）
Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low-level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency…
Image quality assessment (IQA) aims to assess the perceptual quality of images. The outputs of the IQA algorithms are expected to be consistent with human subjective perception. In image restoration and enhancement tasks, images generated by generative adversarial networks (GAN) can achieve better visual performance than traditional CNN-generated images, although they have spatial shift and texture noise. Unfortunately, the existing IQA methods have unsatisfactory performance on the GAN-based distortion partially because of their low tolerance to spatial misalignment. To this end, we propose t…
Harbin Institute of Technology（哈尔滨工业大学）；City University of Hong Kong（香港城市大学）
Deep learning based image quality assessment (IQA) models usually learn to predict image quality from a single dataset, leading the model to overfit specific scenes. To account for this, mixed datasets training can be an effective way to enhance the generalization capability of the model. However, it is nontrivial to combine different IQA datasets, as their quality evaluation criteria, score ranges, view conditions, as well as subjects are usually not shared during the image quality annotation. In this paper, instead of aligning the annotations, we propose a monotonic neural network for IQA mo…
Image quality assessment that aims at estimating the subject quality of images, builds models to evaluate the perceptual quality of the image in different applications. Based on the fact that the human visual system (HVS) is highly sensitive to structural information, the edge information extraction is widely applied in different IQA metrics. According to previous studies, the image gradient magnitude (GM) and the Laplacian of Gaussian (LOG) operator are two efficient structural features in IQA tasks. However, most of the IQA metrics achieve good performance only when the distorted image is to…
Perceptual Depth Quality Assessment of Stereoscopic Omnidirectional Images
School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）；Department of Electrical and Computer Engineering, University of Waterloo（滑铁卢大学电气与计算机工程系）
A Hybrid Approach for Unified Image Quality Assessment: Permutation Entropy-Based Features Fused with Random Forest for Natural-Scene and Screen-Content Images for Cross-Content Applications
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
City University of Hong Kong（香港城市大学）；Shanghai Jiao Tong University（上海交通大学）；Jiangxi University of Finance and Economics（江西财经大学）；Nanyang Technological University（南洋理工大学）
Full-reference (FR) image quality assessment (IQA) models assume a high quality "pristine" image as a reference against which to measure perceptual image quality. In many applications, however, the assumption that the reference image is of high quality may be untrue, leading to incorrect perceptual quality predictions. To address this, we propose a new two-step image quality prediction approach which integrates both no-reference (NR) and full-reference perceptual quality measurements into the quality prediction process. The no-reference module accounts for the possibly imperfect quality of the…
Perceptual image restoration seeks for high-fidelity images that most likely degrade to given images. For better visual quality, previous work proposed to search for solutions within the natural image manifold, by exploiting the latent space of a generative model. However, the quality of generated images are only guaranteed when latent embedding lies close to the prior distribution. In this work, we propose to restrict the feasible region within the prior manifold. This is accomplished with a non-parametric metric for two distributions: the Maximum Mean Discrepancy (MMD). Moreover, we model th…
The enormous space and diversity of natural images is usually represented by a few small-scale human-rated image quality assessment (IQA) datasets. This casts great challenges to deep neural network (DNN) based blind IQA (BIQA), which requires large-scale training data that is representative of the natural image distribution. It is extremely difficult to create human-rated IQA datasets composed of millions of images due to constraints of subjective testing. While a number of efforts have focused on design innovations to enhance the performance of DNN based BIQA, attempts to address the scarcit…
The goal of full-reference image quality assessment (FR-IQA) is to predict the quality of an image as perceived by human observers with using its pristine, reference counterpart. In this study, we explore a novel, combined approach which predicts the perceptual quality of a distorted image by compiling a feature vector from convolutional activation maps. More specifically, a reference-distorted image pair is run through a pretrained convolutional neural network and the activation maps are compared with a traditional image similarity metric. Subsequently, the resulted feature vector is mapped o…
The image Super-Resolution (SR) technique has greatly improved the visual quality of images by enhancing their resolutions. It also calls for an efficient SR Image Quality Assessment (SR-IQA) to evaluate those algorithms or their generated images. In this paper, we focus on the SR-IQA under deep learning and propose a Structure-and-Perception-based Quality Evaluation (SPQE). In emerging deep-learning-based SR, a generated high-quality, visually pleasing image may have different structures from its corresponding low-quality image. In such case, how to balance the quality scores between no-refer…
City University of Hong Kong（香港城市大学）；Noah’s Ark Lab, Huawei Technologies（华为技术有限公司诺亚方舟实验室）
The latest advances in full-reference image quality assessment (IQA) involve unifying structure and texture similarity based on deep representations. The resulting Deep Image Structure and Texture Similarity (DISTS) metric, however, makes rather global quality measurements, ignoring the fact that natural photographic images are locally structured and textured across space and scale. In this paper, we describe a locally adaptive structure and texture similarity index for full-reference IQA, which we term A-DISTS. Specifically, we rely on a single statistical feature, namely the dispersion index…
Gustave Eiffel University（古斯塔夫·埃菲尔大学）；Cardiff University（卡迪夫大学）；Xi'an Jiaotong University（西安交通大学）；Zhongkai University of Agriculture and Engineering（仲恺农业工程学院）；University of Bath（巴斯大学）；Xidian University（西安电子科技大学）
Research on image quality assessment (IQA) remains limited mainly due to our incomplete knowledge about human visual perception. Existing IQA algorithms have been designed or trained with insufficient subjective data with a small degree of stimulus variability. This has led to challenges for those algorithms to handle complexity and diversity of real-world digital content. Perceptual evidence from human subjects serves as a grounding for the development of advanced IQA algorithms. It is thus critical to acquire reliable subjective data with controlled perception experiments that faithfully ref…
Shanghai Jiao Tong University（上海交通大学）；City University of Hong Kong（香港城市大学）
Computational models for blind image quality assessment (BIQA) are typically trained in well-controlled laboratory environments with limited generalizability to realistically distorted images. Similarly, BIQA models optimized for images captured in the wild cannot adequately handle synthetically distorted images. To face the cross-distortion-scenario challenge, we develop a BIQA model and an approach of training it on multiple IQA databases (of different distortion scenarios) simultaneously. A key step in our approach is to create and combine image pairs within individual databases as the trai…
Development of perceptual image quality assessment (IQA) metrics has been of significant interest to computer vision community. The aim of these metrics is to model quality of an image as perceived by humans. Recent works in Full-reference IQA research perform pixelwise comparison between deep features corresponding to query and reference images for quality prediction. However, pixelwise feature comparison may not be meaningful if distortion present in query image is severe. In this context, we explore utilization of no-reference features in Full-reference IQA task. Our model consists of both …
\underline{AI} \underline{G}enerated \underline{C}ontent (\textbf{AIGC}) has gained widespread attention with the increasing efficiency of deep learning in content creation. AIGC, created with the assistance of artificial intelligence technology, includes various forms of content, among which the AI-generated images (AGIs) have brought significant impact to society and have been applied to various fields such as entertainment, education, social media, etc. However, due to hardware limitations and technical proficiency, the quality of AIGC images (AGIs) varies, necessitating refinement and filt…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
No-Reference Image Quality Assessment (NR-IQA) aims to assess the perceptual quality of images in accordance with human subjective perception. Unfortunately, existing NR-IQA methods are far from meeting the needs of predicting accurate quality scores on GAN-based distortion images. To this end, we propose Multi-dimension Attention Network for no-reference Image Quality Assessment (MANIQA) to improve the performance on GAN-based distortion. We firstly extract features via ViT, then to strengthen global and local interactions, we propose the Transposed Attention Block (TAB) and the Scale Swin Tr…
Shanghai Jiao Tong University（上海交通大学）；Polytech Nantes（南特综合理工学院）；Université de Nantes（南特大学）
With the development of multimedia technology, Augmented Reality (AR) has become a promising next-generation mobile platform. The primary value of AR is to promote the fusion of digital contents and real-world environments, however, studies on how this fusion will influence the Quality of Experience (QoE) of these two components are lacking. To achieve better QoE of AR, whose two layers are influenced by each other, it is important to evaluate its perceptual quality first. In this paper, we consider AR technology as the superimposition of virtual scenes and real scenes, and introduce visual co…
Pathology-Guided Virtual Staining Metric for Evaluation and Training
Department of Systems Design Engineering（系统设计工程系）；Department of Applied Mathematics（应用数学系）；Cheriton School of Computer Science（切里顿计算机科学学院）；Department of Biology（生物学系）；School of Pharmacy（药学院）
Bosch Center for AI（博世人工智能中心）；Carnegie Mellon University（卡内基梅隆大学）；University of Pittsburgh（匹兹堡大学）
The goal of No-Reference Image Quality Assessment (NR-IQA) is to estimate the perceptual image quality in accordance with subjective evaluations, it is a complex and unsolved problem due to the absence of the pristine reference image. In this paper, we propose a novel model to address the NR-IQA task by leveraging a hybrid approach that benefits from Convolutional Neural Networks (CNNs) and self-attention mechanism in Transformers to extract both local and non-local features from the input image. We capture local structure information of the image via CNNs, then to circumvent the locality bias…
