HDR-ChipQA: No-Reference Quality Assessment on High Dynamic Range Videos
This addresses the need for better video quality assessment in massively scaled video networks adopting HDR, though it is incremental as it builds on existing natural video statistics features with novel preprocessing.
The authors tackled the problem of accurately assessing video quality for High Dynamic Range (HDR) videos, which have wider luminance and color ranges than Standard Dynamic Range (SDR) videos, by developing HDR-ChipQA, a no-reference model that uses local nonlinear processing to emphasize distortions at extreme luminance ranges and wide-gamut color features, resulting in significant outperformance over SDR VQA algorithms on HDR content and state-of-the-art performance on SDR content.
We present a no-reference video quality model and algorithm that delivers standout performance for High Dynamic Range (HDR) videos, which we call HDR-ChipQA. HDR videos represent wider ranges of luminances, details, and colors than Standard Dynamic Range (SDR) videos. The growing adoption of HDR in massively scaled video networks has driven the need for video quality assessment (VQA) algorithms that better account for distortions on HDR content. In particular, standard VQA models may fail to capture conspicuous distortions at the extreme ends of the dynamic range, because the features that drive them may be dominated by distortions {that pervade the mid-ranges of the signal}. We introduce a new approach whereby a local expansive nonlinearity emphasizes distortions occurring at the higher and lower ends of the {local} luma range, allowing for the definition of additional quality-aware features that are computed along a separate path. These features are not HDR-specific, and also improve VQA on SDR video contents, albeit to a reduced degree. We show that this preprocessing step significantly boosts the power of distortion-sensitive natural video statistics (NVS) features when used to predict the quality of HDR content. In similar manner, we separately compute novel wide-gamut color features using the same nonlinear processing steps. We have found that our model significantly outperforms SDR VQA algorithms on the only publicly available, comprehensive HDR database, while also attaining state-of-the-art performance on SDR content.