Video quality assessment (VQA) is an important problem in computer vision. The videos in computer vision applications are usually captured in the wild. We focus on automatically assessing the quality of in-the-wild videos, which is a challenging problem due to the absence of reference videos, the complexity of distortions, and the diversity of video contents. Moreover, the video contents and distortions among existing datasets are quite different, which leads to poor performance of data-driven methods in the cross-dataset evaluation setting. To improve the performance of quality assessment models, we borrow intuitions from human perception, specifically, content dependency and temporal-memory effects of human visual system. To face the cross-dataset evaluation challenge, we explore a mixed datasets training strategy for training a single VQA model with multiple datasets. The proposed unified framework explicitly includes three stages: relative quality assessor, nonlinear mapping, and dataset-specific perceptual scale alignment, to jointly predict relative quality, perceptual quality, and subjective quality. Experiments are conducted on four publicly available datasets for VQA in the wild, i.e., LIVE-VQC, LIVE-Qualcomm, KoNViD-1k, and CVD2014. The experimental results verify the effectiveness of the mixed datasets training strategy and prove the superior performance of the unified model in comparison with the state-of-the-art models. For reproducible research, we make the PyTorch implementation of our method available at https://github.com/lidq92/MDTVSFA.
Video quality assessment (VQA) methods focus on particular degradation types, usually artificially induced on a small set of reference videos. Hence, most traditional VQA methods under-perform in-the-wild. Deep learning approaches have had limited success due to the small size and diversity of existing VQA datasets, either artificial or authentically distorted. We introduce a new in-the-wild VQA dataset that is substantially larger and diverse: KonVid-150k. It consists of a coarsely annotated set of 153,841 videos having five quality ratings each, and 1,596 videos with a minimum of 89 ratings …
With the rapid growth of in-the-wild videos taken by non-specialists, blind video quality assessment (VQA) has become a challenging and demanding problem. Although lots of efforts have been made to solve this problem, it remains unclear how the human visual system (HVS) relates to the temporal quality of videos. Meanwhile, recent work has found that the frames of natural video transformed into the perceptual domain of the HVS tend to form a straight trajectory of the representations. With the obtained insight that distortion impairs the perceived video quality and results in a curved trajector…
Guangzhou University（广州大学）；Guangdong University of Education（广东第二师范学院）；Xidian University（西安电子科技大学）；Harbin Institute of Technology（哈尔滨工业大学）
The attention mechanism is blooming in computer vision nowadays. However, its application to video quality assessment (VQA) has not been reported. Evaluating the quality of in-the-wild videos is challenging due to the unknown of pristine reference and shooting distortion. This paper presents a novel \underline{s}pace-\underline{t}ime \underline{a}ttention network fo\underline{r} the \underline{VQA} problem, named StarVQA. StarVQA builds a Transformer by alternately concatenating the divided space-time attention. To adapt the Transformer architecture for training, StarVQA designs a vectorized r…
Quality assessment of in-the-wild videos is a challenging problem because of the absence of reference videos and shooting distortions. Knowledge of the human visual system can help establish methods for objective quality assessment of in-the-wild videos. In this work, we show two eminent effects of the human visual system, namely, content-dependency and temporal-memory effects, could be used for this purpose. We propose an objective no-reference video quality assessment method by integrating both effects into a deep neural network. For content-dependency, we extract features from a pre-trained…
Shanghai Jiao Tong University（上海交通大学）；City University of Hong Kong（香港城市大学）
Performance of blind image quality assessment (BIQA) models has been significantly boosted by end-to-end optimization of feature engineering and quality regression. Nevertheless, due to the distributional shift between images simulated in the laboratory and captured in the wild, models trained on databases with synthetic distortions remain particularly weak at handling realistic distortions (and vice versa). To confront the cross-distortion-scenario challenge, we develop a \textit{unified} BIQA model and an approach of training it for both synthetic and realistic distortions. We first sample p…
Perceptual Quality Assessment of Virtual Reality Videos in the Wild
City University of Hong Kong（香港城市大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Jiangxi University of Finance and Economics（江西财经大学）；Bytedance Inc.（字节跳动公司）；National University of Defense Technology（国防科技大学）
Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild
Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University（上海交通大学图像通信与网络工程研究所）；Peng Cheng Laboratory (PCL)（鹏城实验室）；The Hong Kong Polytechnic University（香港理工大学）
Perceptual quality assessment of the videos acquired in the wilds is of vital importance for quality assurance of video services. The inaccessibility of reference videos with pristine quality and the complexity of authentic distortions pose great challenges for this kind of blind video quality assessment (BVQA) task. Although model-based transfer learning is an effective and efficient paradigm for the BVQA task, it remains to be a challenge to explore what and how to bridge the domain shifts for better video representation. In this work, we propose to transfer knowledge from image quality asse…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；Princeton University（普林斯顿大学）
Depth estimation from a single image in the wild remains a challenging problem. One main obstacle is the lack of high-quality training data for images in the wild. In this paper we propose a method to automatically generate such data through Structure-from-Motion (SfM) on Internet videos. The core of this method is a Quality Assessment Network that identifies high-quality reconstructions obtained from SfM. Using this method, we collect single-view depth training data from a large number of YouTube videos and construct a new dataset called YouTube3D. Experiments show that YouTube3D is useful in…
We present a novel formulation to removing reflection from polarized images in the wild. We first identify the misalignment issues of existing reflection removal datasets where the collected reflection-free images are not perfectly aligned with input mixed images due to glass refraction. Then we build a new dataset with more than 100 types of glass in which obtained transmission images are perfectly aligned with input mixed images. Second, capitalizing on the special relationship between reflection and polarized light, we propose a polarized reflection removal model with a two-stage architectu…
University of Konstanz（康斯坦茨大学）；Institute for Computer Science and Control (SZTAKI)（计算机科学与控制研究所（SZTAKI））
Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets. Extensive datasets require substantial resources both for generating publishable content and annotating it accurately. We present a systematic and scalable approach to creating KonIQ-10k, the largest IQA dataset to date, consisting of 10,073 quality scored images. It is the first in-the-wild database aiming for ecological validity, concerning the authenticity of distortions, the diversity of content, and quality-related indicators. Through the use of crowdsourcing, we obtained 1.2 m…
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…
Beijing Electronic Science and Technology Institute（北京电子科技学院）；University of California, Davis（加州大学戴维斯分校）；National Institute of Technology Patna（巴特那国家理工学院）
With the continuous development of social software and multimedia technology, images have become a kind of important carrier for spreading information and socializing. How to evaluate an image comprehensively has become the focus of recent researches. The traditional image aesthetic assessment methods often adopt single numerical overall assessment scores, which has certain subjectivity and can no longer meet the higher aesthetic requirements. In this paper, we construct an new image attribute dataset called aesthetic mixed dataset with attributes(AMD-A) and design external attribute features …
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…
TU Delft（代尔夫特理工大学）；Instituto Tecnologico de Costa Rica（哥斯达黎加技术学院）
Laughter is considered one of the most overt signals of joy. Laughter is well-recognized as a multimodal phenomenon but is most commonly detected by sensing the sound of laughter. It is unclear how perception and annotation of laughter differ when annotated from other modalities like video, via the body movements of laughter. In this paper we take a first step in this direction by asking if and how well laughter can be annotated when only audio, only video (containing full body movement information) or audiovisual modalities are available to annotators. We ask whether annotations of laughter a…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Adobe Research（奥多比研究院）
Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation. But even with modern learning techniques, many inverse problems involving lighting and material understanding remain too severely ill-posed to be solved with single-illumination datasets. To fill this gap, we introduce a new multi-illumination dataset of more than 1000 real scenes, each captured under 25 lighting conditions. We demonstrate the richness of this dataset by training state-of-the-art models for three chal…
City University of Hong Kong（香港城市大学）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
Recently, the group maximum differentiation competition (gMAD) has been used to improve blind image quality assessment (BIQA) models, with the help of full-reference metrics. When applying this type of approach to troubleshoot "best-performing" BIQA models in the wild, we are faced with a practical challenge: it is highly nontrivial to obtain stronger competing models for efficient failure-spotting. Inspired by recent findings that difficult samples of deep models may be exposed through network pruning, we construct a set of "self-competitors," as random ensembles of pruned versions of the tar…
Objective image quality assessment deals with the prediction of digital images' perceptual quality. No-reference image quality assessment predicts the quality of a given input image without any knowledge or information about its pristine (distortion free) counterpart. Machine learning algorithms are heavily used in no-reference image quality assessment because it is very complicated to model the human visual system's quality perception. Moreover, no-reference image quality assessment algorithms are evaluated on publicly available benchmark databases. These databases contain images with their c…
In this work, we present a simple yet effective unified model for perceptual quality assessment of image and video. In contrast to existing models which usually consist of complex network architecture, or rely on the concatenation of multiple branches of features, our model achieves a comparable performance by applying only one global feature derived from a backbone network (i.e. resnet18 in the presented work). Combined with some training tricks, the proposed model surpasses the current baselines of SOTA models on public and private datasets. Based on the architecture proposed, we release the…
WILD: a new in-the-Wild Image Linkage Dataset for synthetic image attribution
University of Siena, Department of Information Engineering an Mathematics, Italy（西尔维亚大学信息工程与数学系，意大利）；Politecnico di Milano, Department of Electronics, Informatics, and Bioengineering, Italy（米兰理工学院电子、信息技术与生物工程系，意大利）；University of Trento, Department of Information Engineering and Computer Science, Italy（特伦托大学信息工程与计算机科学系，意大利）；University of Catania, Department of Mathematics and Computer Science, Italy（卡塔尼亚大学数学与计算机科学系，意大利）；Sapienza University of Rome - Departement of Computer, Control and Management Engineering, Italy（罗马萨皮恩扎大学计算机、控制与管理工程系，意大利）
Conventional methods for visual assessment of civil infrastructures have certain limitations, such as subjectivity of the collected data, long inspection time, and high cost of labor. Although some new technologies i.e. robotic techniques that are currently in practice can collect objective, quantified data, the inspectors own expertise is still critical in many instances since these technologies are not designed to work interactively with human inspector. This study aims to create a smart, human centered method that offers significant contributions to infrastructure inspection, maintenance, m…
Light field (LF) cameras provide rich spatio-angular visual representations by sensing the visual scene from multiple perspectives and have recently emerged as a promising technology to boost the performance of human-machine systems such as biometrics and affective computing. Despite the significant success of LF representation for constrained facial image analysis, this technology has never been used for face and expression recognition in the wild. In this context, this paper proposes a new deep face and expression recognition solution, called CapsField, based on a convolutional neural networ…
Differently from 2D image datasets such as COCO, large-scale human datasets with 3D ground-truth annotations are very difficult to obtain in the wild. In this paper, we address this problem by augmenting existing 2D datasets with high-quality 3D pose fits. Remarkably, the resulting annotations are sufficient to train from scratch 3D pose regressor networks that outperform the current state-of-the-art on in-the-wild benchmarks such as 3DPW. Additionally, training on our augmented data is straightforward as it does not require to mix multiple and incompatible 2D and 3D datasets or to use complic…
Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；Sofia University（索菲亚大学）；University of Macau（澳门大学）；Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shenzhen University of Advanced Technology（深圳先进技术大学）
ETH Zurich（苏黎世联邦理工学院）；Beijing Institute of Technology（北京理工大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
On existing public benchmarks, face forgery detection techniques have achieved great success. However, when used in multi-person videos, which often contain many people active in the scene with only a small subset having been manipulated, their performance remains far from being satisfactory. To take face forgery detection to a new level, we construct a novel large-scale dataset, called FFIW-10K, which comprises 10,000 high-quality forgery videos, with an average of three human faces in each frame. The manipulation procedure is fully automatic, controlled by a domain-adversarial quality assess…
In this work we investigate the use of deep learning for distortion-generic blind image quality assessment. We report on different design choices, ranging from the use of features extracted from pre-trained Convolutional Neural Networks (CNNs) as a generic image description, to the use of features extracted from a CNN fine-tuned for the image quality task. Our best proposal, named DeepBIQ, estimates the image quality by average pooling the scores predicted on multiple sub-regions of the original image. The score of each sub-region is computed using a Support Vector Regression (SVR) machine tak…
University Paris-Est Créteil（巴黎东克雷泰伊大学）；University Paris City（巴黎城市大学）；Istanbul Technical University（伊斯坦布尔理工大学）；National Institute of Technology Warangal（瓦朗加尔国家技术学院）；The National Engineering School of Sfax（斯法克斯国家工程师学院）；French National Centre for Scientific Research（法国国家科学研究中心）
POST-traumatic stress disorder (PTSD) is a chronic and debilitating mental condition that is developed in response to catastrophic life events, such as military combat, sexual assault, and natural disasters. PTSD is characterized by flashbacks of past traumatic events, intrusive thoughts, nightmares, hypervigilance, and sleep disturbance, all of which affect a person's life and lead to considerable social, occupational, and interpersonal dysfunction. The diagnosis of PTSD is done by medical professionals using self-assessment questionnaire of PTSD symptoms as defined in the Diagnostic and Stat…
Face image quality assessment (FIQA) attempts to improve face recognition (FR) performance by providing additional information about sample quality. Because FIQA methods attempt to estimate the utility of a sample for face recognition, it is reasonable to assume that these methods are heavily influenced by the underlying face recognition system. Although modern face recognition systems are known to perform well, several studies have found that such systems often exhibit problems with demographic bias. It is therefore likely that such problems are also present with FIQA techniques. To investiga…
The performance of face recognition system degrades when the variability of the acquired faces increases. Prior work alleviates this issue by either monitoring the face quality in pre-processing or predicting the data uncertainty along with the face feature. This paper proposes MagFace, a category of losses that learn a universal feature embedding whose magnitude can measure the quality of the given face. Under the new loss, it can be proven that the magnitude of the feature embedding monotonically increases if the subject is more likely to be recognized. In addition, MagFace introduces an ada…
Image quality assessment (IQA) is an important element of a broad spectrum of applications ranging from automatic video streaming to display technology. Furthermore, the measurement of image quality requires a balanced investigation of image content and features. Our proposed approach extracts visual features by attaching global average pooling (GAP) layers to multiple Inception modules of on an ImageNet database pretrained convolutional neural network (CNN). In contrast to previous methods, we do not take patches from the input image. Instead, the input image is treated as a whole and is run …
School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）；School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）
With the development of rendering techniques, computer graphics generated images (CGIs) have been widely used in practical application scenarios such as architecture design, video games, simulators, movies, etc. Different from natural scene images (NSIs), the distortions of CGIs are usually caused by poor rending settings and limited computation resources. What's more, some CGIs may also suffer from compression distortions in transmission systems like cloud gaming and stream media. However, limited work has been put forward to tackle the problem of computer graphics generated images' quality a…
