Quality Assessment of Super-Resolved Omnidirectional Image Quality Using Tangential Views

TL;DR

This paper introduces a novel full-reference quality assessment framework for super-resolved omnidirectional images, leveraging tangential views to evaluate GAN-based and CNN-based super-resolution methods, revealing discrepancies between objective metrics and subjective preferences.

Contribution

It proposes a new quality assessment framework for ODIs using tangential views, enabling effective evaluation of super-resolution techniques on spherical data.

Findings

CNN-based SISR methods perform well on objective metrics.

GAN-based SISR methods are preferred in subjective tests.

The framework effectively evaluates super-resolved ODIs using tangential views.

Abstract

Omnidirectional images (ODIs), also known as 360-degree images, enable viewers to explore all directions of a given 360-degree scene from a fixed point. Designing an immersive imaging system with ODI is challenging as such systems require very large resolution coverage of the entire 360 viewing space to provide an enhanced quality of experience (QoE). Despite remarkable progress on single image super-resolution (SISR) methods with deep-learning techniques, no study for quality assessments of super-resolved ODIs exists to analyze the quality of such SISR techniques. This paper proposes an objective, full-reference quality assessment framework which studies quality measurement for ODIs generated by GAN-based and CNN-based SISR methods. The quality assessment framework offers to utilize tangential views to cope with the spherical nature of a given ODIs. The generated tangential views are distortion-free and can be efficiently scaled to high-resolution spherical data for SISR quality measurement. We extensively evaluate two state-of-the-art SISR methods using widely used full-reference SISR quality metrics adapted to our designed framework. In addition, our study reveals that most objective metric show high performance over CNN based SISR, while subjective tests favors GAN-based architectures.