Fully-Automatic Inverse Tone Mapping Preserving the Content Creator’s Artistic Intentions

Abstract

High Dynamic Range (HDR) displays can show images with higher color contrast levels and peak luminosities than the common Low Dynamic Range (LDR) displays. However, most existing video content is recorded and/or graded in LDR format. To show this LDR content on HDR displays, a dynamic range expansion by using an Inverse Tone Mapped Operator (iTMO) is required. In addition to requiring human intervention for tuning, most of the iTMOs don't consider artistic intentions inherent to the HDR domain. Furthermore, the quality of their results decays with peak brightness above 1000 nits. In this paper, we propose a fully-automatic inverse tone mapping operator based on mid-level mapping. This allows expanding LDR images into HDR with peak brightness over 1000 nits, preserving the artistic intentions inherent to the HDR domain. We assessed our results using full-reference objective quality metrics as HDR-VDP-2.2 and DRIM. Experimental results demonstrate that our proposed method outperforms the current state of the art.

Fully-automatic inverse tone mapping algorithm based on dynamic mid-level tone mapping

“…A monotonic function is usually adopted and its shape is adjusted according to the characteristics of the scene present in the image. Typical characteristics are the scene type (dark, average, bright), contrast, amount of saturated pixel, mean and median luminance, and the perceived amount of brightness in the scene [7,[9][10][11]. • Local operators.…”

“…In this article, as an extension of our previous work [7], we describe a fully-automatic inverse tone mapping algorithm based on dynamic mid-level mapping. We carried out an extensive objective evaluation of our algorithm against the most recent methods of inverse tone mapping in the literature.…”

Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies

“…-In order to preserve the lighting style aesthetic, Bist et al [6] also used a gamma curve, which is calculated from the median of the L* component of the input image in the CIE Lab color space. -Luzardo et al [38] proposed a simple non-linear function that maps the middle gray value (0.214 for sRGB linear LDR images) of the input image to that of the output HDR image, where the mid-gray of the HDR image is computed by a linear combination of the geometric mean, the contrast and the percentage of overexposed pixels of the luminance channel of the input image.…”

“…Observers' preferences of ITM methods applied to graded content. From left to right: proposed ITM, Bist et al[6], Luzardo et al[38], Masia et al[42] …”

An experimental study on the perceived quality of natively graded versus inverse tone mapped high dynamic range video content on television

“…As inverse tone mapping expansion operator, we used a novel fully-automatic inverse tone mapping algorithm that is specifically designed to expand SDR video streams to HDR based on mid-level mapping [29]. This algorithm extracts features that represent the contrast, overall brightness and percentage of overexposed pixels in a frame of video and adapts the expansion curve used for the expansion of this frame to reach the most adequate mid-level (overall brightness) on the resulting HDR image.…”