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 pairs of images from individual IQA databases, and compute a probability that the first image of each pair is of higher quality. We then employ the fidelity loss to optimize a deep neural network for BIQA over a large number of such image pairs. We also explicitly enforce a hinge constraint to regularize uncertainty estimation during optimization. Extensive experiments on six IQA databases show the promise of the learned method in blindly assessing image quality in the laboratory and wild. In addition, we demonstrate the universality of the proposed training strategy by using it to improve existing BIQA models.
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…
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…
On the Use of Deep Learning for Blind Image Quality Assessment
University of Milano-Bicocca（米兰比可卡大学）
在这项工作中，我们研究了使用深度学习的失真通用盲图像质量评估。我们报告了不同的设计选择，从使用从预训练的卷积神经网络（CNN）中提取的特征作为通用图像描述，到使用从针对图像质量任务进行微调的CNN中提取的特征。我们最好的建议，名为DeepBIQ，通过平均池化原始图像多个子区域的预测分数来估计图像质量。每个子区域的得分是使用支持向量回归（SVR）机计算的，该支持向量回归机将使用针对基于类别的图像质量评估而微调的CNN提取的特征作为输入。在LIVE In the Wild图像质量挑战数据库和LIVE图像质量评估数据库上的实验结果表明，DeepBIQ的性能优于最先进的方法，与人类主观评分的线性相关系数（LCC）分别接近0.91和0.98。此外，在大多数情况下，DeepBIQ的质量分数预测比一般人类观察者更接近平均观察者。
The research in image quality assessment (IQA) has a long history, and significant progress has been made by leveraging recent advances in deep neural networks (DNNs). Despite high correlation numbers on existing IQA datasets, DNN-based models may be easily falsified in the group maximum differentiation (gMAD) competition with strong counterexamples being identified. Here we show that gMAD examples can be used to improve blind IQA (BIQA) methods. Specifically, we first pre-train a DNN-based BIQA model using multiple noisy annotators, and fine-tune it on multiple subject-rated databases of synt…
University of Engineering and Technology Lahore（拉合尔工程技术大学）
The assessment of the perceptual quality of digital images is becoming increasingly important as a result of the widespread use of digital multimedia devices. Smartphones and high-speed internet are just two examples of technologies that have multiplied the amount of multimedia content available. Thus, obtaining a representative dataset, which is required for objective quality assessment training, is a significant challenge. The Blind Image Quality Assessment Database, BIQ2021, is presented in this article. By selecting images with naturally occurring distortions and reliable labeling, the dat…
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；The Hong Kong Polytechnic University（香港理工大学）
Blind face restoration (BFR) from severely degraded face images in the wild is a very challenging problem. Due to the high illness of the problem and the complex unknown degradation, directly training a deep neural network (DNN) usually cannot lead to acceptable results. Existing generative adversarial network (GAN) based methods can produce better results but tend to generate over-smoothed restorations. In this work, we propose a new method by first learning a GAN for high-quality face image generation and embedding it into a U-shaped DNN as a prior decoder, then fine-tuning the GAN prior emb…
Diffusion models have shown promising results on single-image super-resolution and other image- to-image translation tasks. Despite this success, they have not outperformed state-of-the-art GAN models on the more challenging blind super-resolution task, where the input images are out of distribution, with unknown degradations. This paper introduces SR3+, a diffusion-based model for blind super-resolution, establishing a new state-of-the-art. To this end, we advocate self-supervised training with a combination of composite, parameterized degradations for self-supervised training, and noise-cond…
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；The Hong Kong Polytechnic University（香港理工大学）
In supervised image restoration tasks, one key issue is how to obtain the aligned high-quality (HQ) and low-quality (LQ) training image pairs. Unfortunately, such HQ-LQ training pairs are hard to capture in practice, and hard to synthesize due to the complex unknown degradation in the wild. While several sophisticated degradation models have been manually designed to synthesize LQ images from their HQ counterparts, the distribution gap between the synthesized and real-world LQ images remains large. We propose a new approach to synthesizing realistic image restoration training pairs using the e…
This paper introduces a method to encode the blur operators of an arbitrary dataset of sharp-blur image pairs into a blur kernel space. Assuming the encoded kernel space is close enough to in-the-wild blur operators, we propose an alternating optimization algorithm for blind image deblurring. It approximates an unseen blur operator by a kernel in the encoded space and searches for the corresponding sharp image. Unlike recent deep-learning-based methods, our system can handle unseen blur kernel, while avoiding using complicated handcrafted priors on the blur operator often found in classical me…
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…
Recently, facial expression recognition (FER) in the wild has gained a lot of researchers' attention because it is a valuable topic to enable the FER techniques to move from the laboratory to the real applications. In this paper, we focus on this challenging but interesting topic and make contributions from three aspects. First, we present a new large-scale 'in-the-wild' dynamic facial expression database, DFEW (Dynamic Facial Expression in the Wild), consisting of over 16,000 video clips from thousands of movies. These video clips contain various challenging interferences in practical scenari…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google LLC（谷歌有限责任公司）
Recent years have witnessed an explosion of user-generated content (UGC) videos shared and streamed over the Internet, thanks to the evolution of affordable and reliable consumer capture devices, and the tremendous popularity of social media platforms. Accordingly, there is a great need for accurate video quality assessment (VQA) models for UGC/consumer videos to monitor, control, and optimize this vast content. Blind quality prediction of in-the-wild videos is quite challenging, since the quality degradations of UGC content are unpredictable, complicated, and often commingled. Here we contrib…
PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentation
The University of Queensland（昆士兰大学）；School of Electrical Engineering and Computer Science, The University of Queensland（昆士兰大学电气工程与计算机科学学院）；School of Agriculture and Food Sustainability, The University of Queensland（昆士兰大学农业与食品可持续发展学院）；CSIRO（联邦科学与工业研究组织）
Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild
Faculty of Computer and Information Science, University of Ljubljana（卢布尔雅那大学计算机与信息科学学院）；Faculty of Electrical Engineering, University of Ljubljana（卢布尔雅那大学电气工程学院）
Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge
Flensburg University of Applied Sciences（弗劳恩霍夫应用科技大学）；Technische Hochschule Ingolstadt（施特拉尔松德应用技术大学）；University of Veterinary Medicine（兽医大学）；Schwarzman Animal Medical Center（施瓦茨曼动物医学中心）；Freie Universität Berlin（柏林自由大学）；University of Warwick（沃里克大学）；MINES Paris - PSL University（巴黎综合理工学院）；Yildiz Technical University（耶利泽技术大学）；University College London（伦敦大学学院）；AIRA MATRIX Private Limited（AIRA MATRIX 私人有限公司）；University of California, Los Angeles（加州大学洛杉矶分校）；University of Kansas Medical Center（堪萨斯医学中心）；University of Salerno（萨勒诺大学）；Cancer Center Sp. z o. o.（癌症中心）；th Military Research Hospital in Bydgoszcz（比多日茨军医研究所）；Shenzhen Technology University（深圳技术大学）；Toronto Metropolitan University（多伦多 Metropolitan 大学）；Tata Consultancy Services Ltd.（塔塔咨询有限公司）；Leeds Teaching Hospitals NHS Trust（利兹教学医院 NHS信托）；The University of Tokyo（东京大学）；Xi’an Jiaotong-Liverpool University（西安交通大学-利物浦大学）；University of Augsburg（奥格斯堡大学）；Ulm University（乌尔姆大学）；Japanese Red Cross Medical Center（日本红十字医疗中心）；Wroclaw University of Science and Technology（沃拉日市科学与技术大学）；TECNALIA, Basque Research and Technology Alliance (BRTA)（TECNALIA，巴斯克研究与技术联盟（BRTA））；Indian Institute of Technology Bombay（孟买印度理工学院）；MBZUAI；University of Basel（巴塞尔大学）；University Medical Center Utrecht（乌得勒支大学医学中心）；TU Eindhoven（埃因霍温理工大学）；HUN-REN Biological Research Centre（匈牙利-人生物研究中心）
