TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Triplets

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sureddi, Rajesh, Zadtootaghaj, Saman, Barman, Nabajeet, Bovik, Alan C.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908453955436544
author Sureddi, Rajesh
Zadtootaghaj, Saman
Barman, Nabajeet
Bovik, Alan C.
author_facet Sureddi, Rajesh
Zadtootaghaj, Saman
Barman, Nabajeet
Bovik, Alan C.
contents Image Quality Assessment (IQA) models aim to predict perceptual image quality in alignment with human judgments. No-Reference (NR) IQA remains particularly challenging due to the absence of a reference image. While deep learning has significantly advanced this field, a major hurdle in developing NR-IQA models is the limited availability of subjectively labeled data. Most existing deep learning-based NR-IQA approaches rely on pre-training on large-scale datasets before fine-tuning for IQA tasks. To further advance progress in this area, we propose a novel approach that constructs a custom dataset using a limited number of reference content images and introduces a no-reference IQA model that incorporates both content and quality features for perceptual quality prediction. Specifically, we train a quality-aware model using contrastive triplet-based learning, enabling efficient training with fewer samples while achieving strong generalization performance across publicly available datasets. Our repository is available at https://github.com/rajeshsureddi/triqa.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Triplets
Sureddi, Rajesh
Zadtootaghaj, Saman
Barman, Nabajeet
Bovik, Alan C.
Image and Video Processing
Computer Vision and Pattern Recognition
Image Quality Assessment (IQA) models aim to predict perceptual image quality in alignment with human judgments. No-Reference (NR) IQA remains particularly challenging due to the absence of a reference image. While deep learning has significantly advanced this field, a major hurdle in developing NR-IQA models is the limited availability of subjectively labeled data. Most existing deep learning-based NR-IQA approaches rely on pre-training on large-scale datasets before fine-tuning for IQA tasks. To further advance progress in this area, we propose a novel approach that constructs a custom dataset using a limited number of reference content images and introduces a no-reference IQA model that incorporates both content and quality features for perceptual quality prediction. Specifically, we train a quality-aware model using contrastive triplet-based learning, enabling efficient training with fewer samples while achieving strong generalization performance across publicly available datasets. Our repository is available at https://github.com/rajeshsureddi/triqa.
title TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Triplets
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.12687