HIDRO-VQA: High Dynamic Range Oracle for Video Quality Assessment
This addresses the growing need for quality assessment tools for HDR videos, which have unique distortions compared to standard videos, though it is incremental as it adapts existing methods to a new domain.
The paper tackles the problem of video quality assessment for High Dynamic Range (HDR) videos by proposing HIDRO-VQA, a no-reference model that uses self-supervised contrastive fine-tuning to transfer features from Standard Dynamic Range to HDR domains, achieving state-of-the-art performance on the LIVE-HDR VQA database.
We introduce HIDRO-VQA, a no-reference (NR) video quality assessment model designed to provide precise quality evaluations of High Dynamic Range (HDR) videos. HDR videos exhibit a broader spectrum of luminance, detail, and color than Standard Dynamic Range (SDR) videos. As HDR content becomes increasingly popular, there is a growing demand for video quality assessment (VQA) algorithms that effectively address distortions unique to HDR content. To address this challenge, we propose a self-supervised contrastive fine-tuning approach to transfer quality-aware features from the SDR to the HDR domain, utilizing unlabeled HDR videos. Our findings demonstrate that self-supervised pre-trained neural networks on SDR content can be further fine-tuned in a self-supervised setting using limited unlabeled HDR videos to achieve state-of-the-art performance on the only publicly available VQA database for HDR content, the LIVE-HDR VQA database. Moreover, our algorithm can be extended to the Full Reference VQA setting, also achieving state-of-the-art performance. Our code is available publicly at https://github.com/avinabsaha/HIDRO-VQA.