Perceptual Assessment and Optimization of HDR Image Rendering
This work addresses the need for better quality assessment tools in HDR imaging, which is crucial for applications like novel view synthesis, but it is incremental as it builds on established LDR metrics.
The paper tackles the problem of accurately assessing the quality of high dynamic range (HDR) image rendering, which is underexplored compared to low dynamic range (LDR) images, by proposing a family of HDR quality metrics that decompose HDR images into LDR stacks for assessment using existing LDR metrics, resulting in consistent outperformance of existing models on four HDR datasets and in perceptual optimization tasks.
High dynamic range (HDR) rendering has the ability to faithfully reproduce the wide luminance ranges in natural scenes, but how to accurately assess the rendering quality is relatively underexplored. Existing quality models are mostly designed for low dynamic range (LDR) images, and do not align well with human perception of HDR image quality. To fill this gap, we propose a family of HDR quality metrics, in which the key step is employing a simple inverse display model to decompose an HDR image into a stack of LDR images with varying exposures. Subsequently, these decomposed images are assessed through well-established LDR quality metrics. Our HDR quality models present three distinct benefits. First, they directly inherit the recent advancements of LDR quality metrics. Second, they do not rely on human perceptual data of HDR image quality for re-calibration. Third, they facilitate the alignment and prioritization of specific luminance ranges for more accurate and detailed quality assessment. Experimental results show that our HDR quality metrics consistently outperform existing models in terms of quality assessment on four HDR image quality datasets and perceptual optimization of HDR novel view synthesis.