Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Unified and Generalized Approach

2026-04-26

AI Summary

This work addresses the high computational cost and limited generalization inherent in viewport-based approaches for blind omnidirectional image quality assessment (BOIQA) by proposing a unified, viewport-free evaluation framework. The method operates directly on equirectangular projection (ERP) format inputs, effectively reformulating BOIQA as a standard blind image quality assessment (BIQA) problem. This paradigm shift achieves three key advances: viewport independence, architectural unification, and enhanced generalization capability. The proposed deep learning model consistently outperforms existing methods across hold-out testing, cross-database validation, and the gMAD competition, thereby significantly narrowing the performance gap between omnidirectional and conventional 2D image quality assessment.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Blind omnidirectional image quality assessment (BOIQA) presents a great challenge to the visual quality assessment community, due to different storage formats and diverse user viewing behaviors. The main paradigm of BOIQA models includes two steps, ie, viewport generation, and quality prediction, which brings an extra computational burden and is hard to generalize to other visual contents (eg, 2D planar image). Thus, in this paper, we make an attempt to solve these issues. First, we experimentally find that BOIQA can be formulated as a blind (2D planar) image quality assessment (BIQA) problem, ie, the first step - viewport generation - is no longer needed, which narrows the natural gap between BOIQA and BIQA. Then, we present a new BOIQA approach, which has three merits: ie, viewport-unaware - it accepts an omnidirectional image in the widely used equirectangular projection format as input without any transformation; unified - it can also be applied to BIQA; and generalized - it shows better generalizability against other competitors. Finally, we validate its promise by held-out test, cross-database validation, and the well-established gMAD competition.

Problem

• Blind Omnidirectional Image Quality Assessment
• Viewport-Unaware
• Generalization
• Unified Framework
• Equirectangular Projection

Innovation

• viewport-unaware
• blind omnidirectional image quality assessment
• unified framework
• generalization
• equirectangular projection