No Reference Opinion Unaware Quality Assessment of Authentically Distorted Images

Babu, NC and Kannan, V and Soundararajan, R (2023) No Reference Opinion Unaware Quality Assessment of Authentically Distorted Images. In: 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023, 3 - 7 January 2023, Waikoloa, pp. 2458-2467.

PDF wacv_ 2023.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

The quality assessment (QA) of camera captured authentically distorted images is important on account of its ubiquitous applications and challenging due to the lack of a reference. While there exists a plethora of supervised no reference (NR) image QA (IQA) algorithms, there is a need to study unsupervised or opinion unaware algorithms on account of their superior generalization performance. We explore self-supervised learning (SSL) for the feature design on authentically distorted images to predict quality without training on human labels. While SSL on synthetic distortions has recently shown promise, there is a need to enrich the feature learning on authentic distortions. The key challenge in achieving this is in the learning of quality sensitive features with mitigated content dependence. We design a self-supervised contrastive learning approach which only requires positives and introduce a content separation loss by estimating a bound on the mutual information between the features learnt and the content information. We show on multiple authentically distorted datasets that our self-supervised features can predict image quality by comparing with a corpus of pristine images and achieve state-of-the-art performance.§ © 2023 IEEE.

Item Type:	Conference Paper
Publication:	Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Computer vision, Algorithm: low-level and physic-based vision; And algorithm (including transfer, low-shot, semi-, self-, and un-supervised learning); Distorted images; Formulation; Learning architectures; Machine learning architecture; Machine-learning; Physics based vision; Quality assessment; Un-supervised learning, Supervised learning
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	15 Mar 2023 06:06
Last Modified:	15 Mar 2023 06:06
URI:	https://eprints.iisc.ac.in/id/eprint/80990

Actions (login required)

View Item