An Entropy-based Inverse Tone Mapping Operator for High Dynamic Range Applications

Abstract

Conversion of existing image and video content to High Dynamic Range (HDR) using inverse Tone Mapping Operator (iTMO) is expected to open new market opportunities for studios and content owners. In this paper, we propose a novel high visual quality iTMO that addresses shortcomings of existing approaches, yielding HDR image quality worth the expectations of the emerging HDR technology. Our method can deal with all types of standard dynamic range (SDR) image content, ranging from dark to bright scenes. Our approach follows the Human Visual System (HVS) characteristic of being more sensitive to luminance changes in dark areas than bright and normal ones, expanding each of these areas accordingly. Our subjective evaluation demonstrates that our proposed operator on average outperforms existing state-of-the-art operators in terms of overall brightness and contrast of the output HDR image.