# Blind Omnidirectional Image Quality Assessment: Integrating Local Statistics and Global Semantics

arXiv: https://arxiv.org/abs/2302.12393 · HTML: https://mlsanity.com/paper/2302.12393/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 24 Feb 2023.

## Builds on (most cited first, 8 of 8)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Return of the Devil in the Details: Delving Deep into Convolutional Nets](https://mlsanity.com/paper/1405.3531/) (2014)
- [Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks](https://mlsanity.com/paper/2002.09140/) (2020)
- [No-Reference Quality Assessment for 360-degree Images by Analysis of Multi-frequency Information and Local-global Naturalness](https://mlsanity.com/paper/2102.11393/) (2021)
- [Adaptive Hypergraph Convolutional Network for No-Reference 360-degree Image Quality Assessment](https://mlsanity.com/paper/2105.09143/) (2021)
- [Stereoscopic Omnidirectional Image Quality Assessment Based on Predictive Coding Theory](https://mlsanity.com/paper/1906.05165/) (2019)
- [Quality Assessment of Stereoscopic 360-degree Images from Multi-viewports](https://mlsanity.com/paper/1908.10079/) (2019)

## Built on by (most cited first, 3 of 3)

- [MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restoration](https://mlsanity.com/paper/2401.10666/) (2024)
- [Perceptual Visual Quality Assessment: Principles, Methods, and Future Directions](https://mlsanity.com/paper/2503.00625/) (2025)
- [EduVQA: Towards Concept-Aware Assessment of Educational AI-Generated Videos](https://mlsanity.com/paper/2603.03066/) (2026)

## Abstract (arXiv)

Omnidirectional image quality assessment (OIQA) aims to predict the perceptual quality of omnidirectional images that cover the whole 180×360circ viewing range of the visual environment. Here we propose a blind/no-reference OIQA method named S2 that bridges the gap between low-level statistics and high-level semantics of omnidirectional images. Specifically, statistic and semantic features are extracted in separate paths from multiple local viewports and the hallucinated global omnidirectional image, respectively. A quality regression along with a weighting process is then followed that maps the extracted quality-aware features to a perceptual quality prediction. Experimental results demonstrate that the proposed S2 method offers highly competitive performance against state-of-the-art methods.