Adapting Pretrained Networks for Image Quality Assessment on High Dynamic Range Displays

arXiv:2405.00670v1 Announce Type: new
Abstract: Conventional image quality metrics (IQMs), such as PSNR and SSIM, are designed for perceptually uniform gamma-encoded pixel values and cannot be directly applied to perceptually non-uniform linear high-dynamic-range (HDR) colors. Similarly, most of the available datasets consist of standard-dynamic-range (SDR) images collected in standard and possibly uncontrolled viewing conditions. Popular pre-trained neural networks are likewise intended for SDR inputs, restricting their direct application to HDR content. On the other hand, training HDR models from scratch …

abstract arxiv assessment colors cs.cv datasets dynamic eess.iv image images linear metrics networks pixel quality standard type uniform values