Domain-Aware No-Reference Image Quality Assessment

by   Weihao Xia, et al.

No-reference image quality assessment (NR-IQA) is a fundamental yet challenging task in low-level computer vision. It is to predict the perceptual quality of an image with unknown distortion. Its difficulty is particularly pronounced as the corresponding reference for assessment is typically absent. Various mechanisms to extract features ranging from natural scene statistics to deep features have been leveraged to boost the NR-IQA performance. However, these methods treat images of different degradations the same and the representations of distortions are under-exploited. Furthermore, identifying the distortion type should be an important part for NR-IQA, which is rarely addressed in the previous methods. In this work, we propose the domain-aware no-reference image quality assessment (DA-NR-IQA), which for the first time exploits and disentangles the distinct representation of different degradations to access image quality. Benefiting from the design of domain-aware architecture, our method can simultaneously identify the distortion type of an image. With both the by-product distortion type and quality score determined, the distortion in an image can be better characterized and the image quality can be more precisely assessed. Extensive experiments show that the proposed DA-NR-IQA performs better than almost all the other state-of-the-art methods.


page 1

page 3


Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning

No-reference image quality assessment (NR-IQA) is a fundamental yet chal...

Residual Networks based Distortion Classification and Ranking for Laparoscopic Image Quality Assessment

Laparoscopic images and videos are often affected by different types of ...

A Shift-insensitive Full Reference Image Quality Assessment Model Based on Quadratic Sum of Gradient Magnitude and LOG signals

Image quality assessment that aims at estimating the subject quality of ...

Local Distortion Aware Efficient Transformer Adaptation for Image Quality Assessment

Image Quality Assessment (IQA) constitutes a fundamental task within the...

Data-Efficient Image Quality Assessment with Attention-Panel Decoder

Blind Image Quality Assessment (BIQA) is a fundamental task in computer ...

Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

We aim at advancing blind image quality assessment (BIQA), which predict...

Deep No-reference Tone Mapped Image Quality Assessment

The process of rendering high dynamic range (HDR) images to be viewed on...

Please sign up or login with your details

Forgot password? Click here to reset