We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for regression, which makes it significantly deeper than related IQA models. Unique features of the proposed architecture are that: 1) with slight adaptations it can be used in a no-reference (NR) as well as in a full-reference (FR) IQA setting and 2) it allows for joint learning of local quality and local weights, i.e., relative importance of local quality to the global quality estimate, in an unified framework. Our approach is purely data-driven and does not rely on hand-crafted features or other types of prior domain knowledge about the human visual system or image statistics. We evaluate the proposed approach on the LIVE, CISQ, and TID2013 databases as well as the LIVE In the wild image quality challenge database and show superior performance to state-of-the-art NR and FR IQA methods. Finally, cross-database evaluation shows a high ability to generalize between different databases, indicating a high robustness of the learned features.

Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

Since human observers are the ultimate receivers of digital images, image quality metrics should be designed from a human-oriented perspective. Conventionally, a number of full-reference image quality assessment (FR-IQA) methods adopted various computational models of the human visual system (HVS) from psychological vision science research. In this paper, we propose a novel convolutional neural networks (CNN) based FR-IQA model, named Deep Image Quality Assessment (DeepQA), where the behavior of the HVS is learned from the underlying data distribution of IQA databases. Different from previous studies, our model seeks the optimal visual weight based on understanding of database information itself without any prior knowledge of the HVS. Through the experiments, we show that the predicted visual sensitivity maps agree with the human subjective opinions. In addition, DeepQA achieves the state-of-the-art prediction accuracy among FR-IQA models.

/pdf/deep-learning-of-human-visual-sensitivity-in-image-quality-2viafjhd8l.pdf

Deep Learning of Human Visual Sensitivity in Image Quality Assessment Framework

Smartphones and other consumer devices capable of capturing video content and sharing it on social media in nearly real time are widely available at a reasonable cost. Thus, there is a growing need for no-reference video quality assessment (NR-VQA) of consumer produced video content, typically characterized by capture impairments that are qualitatively different from those observed in professionally produced video content. To date, most of the NR-VQA models in prior art have been developed for assessing coding and transmission distortions, rather than capture impairments. In addition, the most accurate NR-VQA methods known in prior art are often computationally complex, and therefore impractical for many real life applications. In this paper, we propose a new approach for learning-based video quality assessment, based on the idea of computing features in two levels so that low complexity features are computed for the full sequence first, and then high complexity features are extracted from a subset of representative video frames, selected by using the low complexity features. We have compared the proposed method against several relevant benchmark methods using three recently published annotated public video quality databases, and our results show that the proposed method can predict subjective video quality more accurately than the benchmark methods. The best performing prior method achieves nearly similar accuracy, but at substantially higher computational cost.

Two-Level Approach for No-Reference Consumer Video Quality Assessment

The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual differences like humans. Some previous approaches used hand-coded models, but they fail to model the complexity of the human visual system. Others used machine learning to train models on human-labeled datasets, but creating large, high-quality datasets is difficult because people are unable to assign consistent error labels to distorted images. In this paper, we present a new learning-based method that is the first to predict perceptual image error like human observers. Since it is much easier for people to compare two given images and identify the one more similar to a reference than to assign quality scores to each, we propose a new, large-scale dataset labeled with the probability that humans will prefer one image over another. We then train a deep-learning model using a novel, pairwise-learning framework to predict the preference of one distorted image over the other. Our key observation is that our trained network can then be used separately with only one distorted image and a reference to predict its perceptual error, without ever being trained on explicit human perceptual-error labels. The perceptual error estimated by our new metric, PieAPP, is well-correlated with human opinion. Furthermore, it significantly outperforms existing algorithms, beating the state-of-the-art by almost 3A— on our test set in terms of binary error rate, while also generalizing to new kinds of distortions, unlike previous learning-based methods.

/pdf/pieapp-perceptual-image-error-assessment-through-pairwise-311n25g1n1.pdf

PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference

We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear transform codecs for images, and have superseded them in terms of rate–distortion performance under established perceptual quality metrics such as MS-SSIM. We assess the empirical rate–distortion performance of NTC with the help of simple example sources, for which the optimal performance of a vector quantizer is easier to estimate than with natural data sources. To this end, we introduce a novel variant of entropy-constrained vector quantization. We provide an analysis of various forms of stochastic optimization techniques for NTC models; review architectures of transforms based on artificial neural networks, as well as learned entropy models; and provide a direct comparison of a number of methods to parameterize the rate–distortion trade-off of nonlinear transforms, introducing a simplified one.

/pdf/nonlinear-transform-coding-402wbjdyjh.pdf

Nonlinear Transform Coding

Objective image quality assessment (IQA) plays an important role in the development of multimedia applications. Prediction of IQA metric should be consistent with human perception. The release of the newest IQA database (TID2013) challenges most of the widely used quality metrics (e.g., peak-to-noise-ratio and structure similarity index). We propose a new methodology to build the metric model using a regression approach. The new IQA score is set to be the nonlinear combination of features extracted from several difference of Gaussian (DOG) frequency bands, which mimics the human visual system (HVS). Experimental results show that the random forest regression model trained by the proposed DOG feature is highly correspondent to the HVS and is also robust when tested by available databases.

Image Quality Assessment Using Human Visual DOG Model Fused With Random Forest

Many objective video quality assessment (VQA) algorithms include a key step of temporal pooling of frame-level quality scores. However, less attention has been paid to studying the relative efficiencies of different pooling methods on noreference (blind) VQA. Here we conduct a large-scale comparative evaluation to assess the capabilities and limitations of multiple temporal pooling strategies on blind VQA of usergenerated videos. The study yields insights and general guidance regarding the application and selection of temporal pooling models. In addition, we also propose an ensemble pooling model built on top of high-performing temporal pooling models. Our experimental results demonstrate the relative efficacies of the evaluated temporal pooling models, using several popular VQA algorithms evaluated on two recent largescale natural video quality databases. Conclusively, we also provide an empirical recipe for applying temporal pooling of frame-based quality predictions.

A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment

The use of $\ell _{p}$ (p = 1,2) norms has largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess the loss of visual information, these simple norms are not very consistent with human perception. Here, we describe a different “proximal” approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, broadly termed ProxIQA, which mimics the perceptual model while serving as a loss layer of the network. We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of an existing deep image compression model, we are able to demonstrate a bitrate reduction of as much as 31% over MSE optimization, given a specified perceptual quality (VMAF) level.

ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression

Modeling image and video distortions is an important, but difficult problem of great consequence to numerous and diverse image processing and computer vision applications. While many statistical models have been proposed to synthesize different types of image noise, real-world distortions are far more difficult to emulate. Toward advancing progress on this interesting problem, we consider distortion generation as an image-to-image transformation problem, and solve it via a data-driven approach. Specifically, we use a conditional generative adversarial network (cGAN) which we train to learn four kinds of realistic distortions. We experimentally demonstrate that the learned model can produce the perceptual characteristics of several types of distortion.

Learning to Distort Images Using Generative Adversarial Networks

Measuring the quality of digital videos viewed by human observers has become a common practice in numerous multimedia applications, such as adaptive video streaming, quality monitoring, and other digital TV applications. Here we explore a significant, yet relatively unexplored problem: measuring perceptual quality on videos arising from both luma and chroma distortions from compression. Toward investigating this problem, it is important to understand the kinds of chroma distortions that arise, how they relate to luma compression distortions, and how they can affect perceived quality. We designed and carried out a subjective experiment to measure subjective video quality on both luma and chroma distortions, introduced both in isolation as well as together. Specifically, the new subjective dataset comprises a total of 210 videos afflicted by distortions caused by varying levels of luma quantization commingled with different amounts of chroma quantization. The subjective scores were evaluated by 34 subjects in a controlled environmental setting. Using the newly collected subjective data, we were able to demonstrate important shortcomings of existing video quality models, especially in regards to chroma distortions. Further, we designed an objective video quality model which builds on existing video quality algorithms, by considering the fidelity of chroma channels in a principled way. We also found that this quality analysis implies that there is room for reducing bitrate consumption in modern video codecs by creatively increasing the compression factor on chroma channels. We believe that this work will both encourage further research in this direction, as well as advance progress on the ultimate goal of jointly optimizing luma and chroma compression in modern video encoders.

Li-Heng Chen

Papers

Image Quality Assessment Using Human Visual DOG Model Fused With Random Forest

A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment

ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression

Learning to Distort Images Using Generative Adversarial Networks

Perceptual Video Quality Prediction Emphasizing Chroma Distortions