ARNIQA: Learning Distortion Manifold for Image Quality Assessment
Authors:
Top Cited Papers
- 3 January 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 188-197
Abstract
No-Reference Image Quality Assessment (NR-IQA) aims to develop methods to measure image quality in alignment with human perception without the need for a high-quality reference image. In this work, we propose a self-supervised approach named ARNIQA (leArning distoRtion maNifold for Image Quality Assessment) for modeling the image distortion manifold to obtain quality representations in an intrinsic manner. First, we introduce an image degradation model that randomly composes ordered sequences of consecutively applied distortions. In this way, we can synthetically degrade images with a large variety of degradation patterns. Second, we propose to train our model by maximizing the similarity between the representations of patches of different images distorted equally, despite varying content. Therefore, images degraded in the same manner correspond to neighboring positions within the distortion manifold. Finally, we map the image representations to the quality scores with a simple linear regressor, thus without fine-tuning the encoder weights. The experiments show that our approach achieves state-of-the-art performance on several datasets. In addition, ARNIQA demonstrates improved data efficiency, generalization capabilities, and robustness compared to competing methods. The code and the model are publicly available at https://github.com/miccunifi/ARNIQA.Keywords
All Related Versions
Funding Information
- European Commission
This publication has 35 references indexed in Scilit:
- From Distortion Manifold to Perceptual Quality: a Data Efficient Blind Image Quality Assessment ApproachPattern Recognition, 2022
- Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel2022
- GIQE: Generic Image Quality Enhancement via Nth Order Iterative Degradation2022
- Perceptual Quality Assessment of Smartphone Photography2020
- Assessing Image Quality Issues for Real-World Problems2020
- Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network2020
- From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Group MAD Competition? A New Methodology to Compare Objective Image Quality Models2016
- Unsupervised feature learning framework for no-reference image quality assessment2012