Deep Multi-Scale Features Learning for Distorted Image Quality Assessment

  title={Deep Multi-Scale Features Learning for Distorted Image Quality Assessment},
  author={Wei Zhou and Zhibo Chen},
  journal={2021 IEEE International Symposium on Circuits and Systems (ISCAS)},
  • Wei Zhou, Zhibo Chen
  • Published 1 December 2020
  • Computer Science
  • 2021 IEEE International Symposium on Circuits and Systems (ISCAS)
Image quality assessment (IQA) aims to estimate human perception based image visual quality. Although existing deep neural networks (DNNs) have shown significant effectiveness for tackling the IQA problem, it still needs to improve the DNN- based quality assessment models by exploiting efficient multi- scale features. In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with… 

Figures and Tables from this paper

IQMA Network: Image Quality Multi-scale Assessment Network

A bilateral-branch multi-scale image quality estimation network, named IQMA network, designed with Feature Pyramid Network (FPN)-like architecture, which consistently outperforms existing state-of-the-art (SOTA) methods on LIVE and TID2013.

Image quality assessment based on the image contents visual perception

Analysis and comparison show that the proposed IQA method and mathematical model are an excellent IQA model on performance, whose comprehensive efficiency is better than ones of the seven existing IQA models.

Fractal pyramid low-light image enhancement network with illumination information

A two-stage low-light image enhancement network called the fractal pyramid network with illumination information (FPN-IL) is proposed, which is able to make full use of contextual information and interactions of features at different scales and could be abundant.

Vehicle detection method based on adaptive multi-scale feature fusion network

The proposed adaptive multi-scale feature fusion network (AMFFN) fuses features of multiple scales across layers and assigns learnable weights to layers of different scales and depthwise separable convolution is used to replace the normal convolution and increase the speed of detection.



DeepSim: Deep similarity for image quality assessment

Image Quality Assessment Based on Local Linear Information and Distortion-Specific Compensation

A novel IQA method is developed based on a local linear model that examines the distortion between the reference and the distorted images for better alignment with human visual experience and an integrated IQA metric is proposed by combining the aforementioned two ideas.

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

A deep neural network-based approach to image quality assessment (IQA) that allows for joint learning of local quality and local weights in an unified framework and shows a high ability to generalize between different databases, indicating a high robustness of the learned features.

Binocular Rivalry Oriented Predictive Autoencoding Network for Blind Stereoscopic Image Quality Measurement

This article develops a Predictive Auto-encoDing Network (PAD-Net) for blind/no-reference SIQM, inspired by the predictive coding theory that the cognition system tries to match bottom–up visual signal with top–down predictions, and adopts the encoder–decoder architecture to reconstruct the distorted inputs.

Dual-Stream Interactive Networks for No-Reference Stereoscopic Image Quality Assessment

The experimental results show that the proposed StereoQA-Net outperforms state-of-the-art algorithms on both symmetrically and asymmetrically distorted stereoscopic image pairs of various distortion types and can effectively predict the perceptual quality of local regions.

FSIM: A Feature Similarity Index for Image Quality Assessment

A novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features.

Deep Multi-patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation

The proposed deep multi-patch aggregation network integrates shared feature learning and aggregation function learning into a unified framework and significantly outperformed the state of the art in all three applications.

Quality Assessment for Comparing Image Enhancement Algorithms

This paper proposes a framework to do quality assessment for comparing image enhancement algorithms, and focuses on the relative quality ranking between enhanced images rather than giving an absolute quality score for a single enhanced image.

Information Content Weighting for Perceptual Image Quality Assessment

This paper aims to test the hypothesis that when viewing natural images, the optimal perceptual weights for pooling should be proportional to local information content, which can be estimated in units of bit using advanced statistical models of natural images.