Quality Assessment and Distortion-aware Saliency Prediction for AI-Generated Omnidirectional Images

TL;DR

This paper introduces a new database and models for assessing quality and predicting saliency in AI-generated omnidirectional images, improving VR/AR applications by enhancing visual quality.

Contribution

It presents the OHF2024 database and two novel models, BLIP2OIQA and BLIP2OISal, for quality assessment and saliency prediction of AI-generated omnidirectional images, along with an optimization process.

Findings

Models achieve state-of-the-art results in quality evaluation.

Models effectively predict distortion-aware saliency.

Optimization improves visual quality of AI-generated images.

Abstract

With the rapid advancement of Artificial Intelligence Generated Content (AIGC) techniques, AI generated images (AIGIs) have attracted widespread attention, among which AI generated omnidirectional images (AIGODIs) hold significant potential for Virtual Reality (VR) and Augmented Reality (AR) applications. AI generated omnidirectional images exhibit unique quality issues, however, research on the quality assessment and optimization of AI-generated omnidirectional images is still lacking. To this end, this work first studies the quality assessment and distortion-aware saliency prediction problems for AIGODIs, and further presents a corresponding optimization process. Specifically, we first establish a comprehensive database to reflect human feedback for AI-generated omnidirectionals, termed OHF2024, which includes both subjective quality ratings evaluated from three perspectives and distortion-aware salient regions. Based on the constructed OHF2024 database, we propose two models with shared encoders based on the BLIP-2 model to evaluate the human visual experience and predict distortion-aware saliency for AI-generated omnidirectional images, which are named as BLIP2OIQA and BLIP2OISal, respectively. Finally, based on the proposed models, we present an automatic optimization process that utilizes the predicted visual experience scores and distortion regions to further enhance the visual quality of an AI-generated omnidirectional image. Extensive experiments show that our BLIP2OIQA model and BLIP2OISal model achieve state-of-the-art (SOTA) results in the human visual experience evaluation task and the distortion-aware saliency prediction task for AI generated omnidirectional images, and can be effectively used in the optimization process. The database and codes will be released on https://github.com/IntMeGroup/AIGCOIQA to facilitate future research.