Convolutional Neural Networks for No-Reference Image Quality Assessment

By Le Kang, Peng Ye, Yi Li, David S. Doermann. 2014

1,187 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

The Perception-Distortion Tradeoff (2017, methodology): “[25, 26, 33, 27, 45, 16, 23], which quantify the perceptual quality of an image without a corresponding original image.”
Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “In addition, we compare the original results of BRISQUE, BLIINDS, CORNIA, and CNNIQA in Table 10 and Figure 13.”
Vehicle Type Classification Using a Semisupervised Convolutional Neural Network (2015, methodology): “It has been used to learn good features in face detection [18], [19], facial point detection [20], pedestrian detection [21], human attribute inference [22], image quality assessment [23], image classification [24], and video classification [25].”
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality (2019, methodology): “The Baseline, RoIPool, and Feedback Models all outperformed the shallow and other deep models [46, 65] on both datasets.”
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling (2022, background): “Naive approaches such as resizing [17,43] and cropping [14,15] cannot preserve video quality well.”
Deep CNN-Based Blind Image Quality Predictor (2019, methodology): “The loss function was similar to [19]; however, they suggested an additional model, which learns the individual importance of each patch.”
MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment (2020, background): “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].”
End-to-End Blind Image Quality Assessment Using Deep Neural Networks (2018, methodology): “ture extraction or a preprocessing step for DNN-based BIQA models [15], [16], [21].”
MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment (2022, methodology): “[3, 14, 20, 37, 61] leveraged the extracted features to predict the subjective score with the help of pre-trained CNN-based models.”
Exploring CLIP for Assessing the Look and Feel of Images (2022, methodology): “In addition, even without task-speciﬁc training, CLIP-IQA out-performs CNNIQA, which requires training with annotations.”
dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, background): “investigated a convolutional neural network to jointly learn features and nonlinear mappings for BIQA [62].”
Photo Aesthetics Ranking Network with Attributes and Content Adaptation (2016, methodology): “CNN for aesthetics classification: In [16,10,17], CNN-based methods are proposed for classifying images into high- or low- aesthetic categories.”
No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency (2021, methodology): “Early version of deep learning NR-IQA methods [31, 45, 46, 34, 46, 35] leveraged deep features from CNNs [29, 30] while pre-trained on large classification dataset ImageNet [47].”
Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, methodology): “With normalized image patches, Kang et al. [29] propose a shallow convolutional neural network (CNN) based BIQA method 1 which could even predict local image quality.”
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network (2020, methodology): “In [14], a simple CNN with pooling strategy inherited from [43] is used for quality prediction.”
TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment (2023, background): “We apply multiple CSA blocks to multi-scale features from pretrained CNN backbones, such as ResNet50 [12].”
Domain Fingerprints for No-Reference Image Quality Assessment (2019, methodology): “4) Evaluation Metrics: Following most previous works [5], [6], [13], the performances on above datasets are evaluated by two common metrics for model evaluation: the Linear Correlation Coefﬁcient (LCC) and the Spearman’s Rank Order Correlation Coefﬁcient (SROCC).”
Fully Deep Blind Image Quality Predictor (2017, methodology): “It is also proved that the CNN structure is effective for IQA [1].”