End-to-End Blind Image Quality Assessment Using Deep Neural Networks

By Kede Ma, Wentao Liu, Kai Zhang, Zhengfang Duanmu, Zhou Wang, Wangmeng Zuo. IEEE Transactions on Image Processing, 2018

556 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/fcce2d6be712765ffef7943ab364d1652db2820a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment (2020, methodology): “Recent years have witnessed the great success of Deep Convolutional Neural Networks (DCNNs) [14] in many computer vision tasks [4, 5], which has also spawned a number of DCNNs-based NR-IQA approaches [16, 2, 28, 30, 52, 58, 57].”
Exploring CLIP for Assessing the Look and Feel of Images (2022, methodology): “To alleviate the problem, later methods [1, 18, 22, 25, 26, 30, 48, 61] resort to the learning-based paradigm, where a quality predictive model is directly learned from manually labeled data.”
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective (2023, background): “, Gaussian noise and JPEG compression) are of primary concern, patchwise training [4], quality-aware pre-training [32, 37, 76], and learning from noisy pseudolabels [2, 38, 67] are practical training tricks with less (or no) reliance on MOSs.”
Perceptual Quality Assessment of Smartphone Photography (2020, background): “Early BIQA models [4, 20–23, 39] mainly focus on synthetic distortions, which have been empirically shown to generalize poorly to realistic camera distortions [5, 41].”
Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser (2020, methodology): “Performance should ultimately be tested using experiments with human observers, which might be approximated using using a no-reference perceptual quality metric (e.g., [55]).”
No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency (2021, methodology): “[38, 64] extracted binary ranking information via FR-IQA methods during the training.”
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network (2020, background): “[27] proposed a deeper network to learn distortion type and image quality simultaneously.”
MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment (2022, methodology): “With the success of deep learning and Convolution Neural Network (CNN) in many computer vision tasks, CNN-based methods have significantly outperformed previous approaches in terms of real-world distortions by directly extracting discriminative features from LQ images [1,3,14,20,26,37,39,45,59,61].”
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality (2019, background): “Several deep NR models [42, 43, 44, 45, 46] have also been created that yield state-of-the-art performance on legacy synthetic distortion databases [3, 4, 26, 41], by pretraining deep nets [47, 48, 49] on ImageNet [50], then fine tuning, or by training on proxy labels generated by an FR model [45].”
KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment (2019, methodology): “Ma et al. [41] proposed the MEON model.”
Domain Fingerprints for No-Reference Image Quality Assessment (2019, methodology): “For pre-training, as in the previous studies [4], [44], we reproduce 17 out of a total of 24 distortion types in TID2013 and apply them to the 840 high-quality images.”
Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network (2019, methodology): “Until recently, there has been limited effort towards end-to-end optimized BIQA using deep convolutional neural networks (CNN) [10], [11], primarily due to the lack of sufficient ground truth labels such as the mean opinion scores (MOS) for training.”
Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild (2020, methodology): “The third method is quality-aware pre-training, which automatically generates a large amount of labeled data by exploiting speciﬁcations of distortion processes or quality estimates of full-reference models [3], [14], [30].”
TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment (2023, background): “They are generally improved with more advanced network architecture, from deep belief net [36] to CNN [37], then to deeper CNN [38], [39], [40], later to ResNet [41], [42], [43], and now vision transformers [44], [45], [46].”