LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Avanaki, Nasim Jamshidi, Ghildyal, Abhijay, Barman, Nabajeet, Zadtootaghaj, Saman
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917770134814720
author Avanaki, Nasim Jamshidi
Ghildyal, Abhijay
Barman, Nabajeet
Zadtootaghaj, Saman
author_facet Avanaki, Nasim Jamshidi
Ghildyal, Abhijay
Barman, Nabajeet
Zadtootaghaj, Saman
contents Recent advancements in the field of No-Reference Image Quality Assessment (NR-IQA) using deep learning techniques demonstrate high performance across multiple open-source datasets. However, such models are typically very large and complex making them not so suitable for real-world deployment, especially on resource- and battery-constrained mobile devices. To address this limitation, we propose a compact, lightweight NR-IQA model that achieves state-of-the-art (SOTA) performance on ECCV AIM UHD-IQA challenge validation and test datasets while being also nearly 5.7 times faster than the fastest SOTA model. Our model features a dual-branch architecture, with each branch separately trained on synthetically and authentically distorted images which enhances the model's generalizability across different distortion types. To improve robustness under diverse real-world visual conditions, we additionally incorporate multiple color spaces during the training process. We also demonstrate the higher accuracy of recently proposed Kolmogorov-Arnold Networks (KANs) for final quality regression as compared to the conventional Multi-Layer Perceptrons (MLPs). Our evaluation considering various open-source datasets highlights the practical, high-accuracy, and robust performance of our proposed lightweight model. Code: https://github.com/nasimjamshidi/LAR-IQA.
format Preprint
id arxiv_https___arxiv_org_abs_2408_17057
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model
Avanaki, Nasim Jamshidi
Ghildyal, Abhijay
Barman, Nabajeet
Zadtootaghaj, Saman
Computer Vision and Pattern Recognition
Multimedia
Image and Video Processing
Recent advancements in the field of No-Reference Image Quality Assessment (NR-IQA) using deep learning techniques demonstrate high performance across multiple open-source datasets. However, such models are typically very large and complex making them not so suitable for real-world deployment, especially on resource- and battery-constrained mobile devices. To address this limitation, we propose a compact, lightweight NR-IQA model that achieves state-of-the-art (SOTA) performance on ECCV AIM UHD-IQA challenge validation and test datasets while being also nearly 5.7 times faster than the fastest SOTA model. Our model features a dual-branch architecture, with each branch separately trained on synthetically and authentically distorted images which enhances the model's generalizability across different distortion types. To improve robustness under diverse real-world visual conditions, we additionally incorporate multiple color spaces during the training process. We also demonstrate the higher accuracy of recently proposed Kolmogorov-Arnold Networks (KANs) for final quality regression as compared to the conventional Multi-Layer Perceptrons (MLPs). Our evaluation considering various open-source datasets highlights the practical, high-accuracy, and robust performance of our proposed lightweight model. Code: https://github.com/nasimjamshidi/LAR-IQA.
title LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model
topic Computer Vision and Pattern Recognition
Multimedia
Image and Video Processing
url https://arxiv.org/abs/2408.17057