Quality-driven tone-mapping operator: a pseudo-exposure fusion-based approach
- PDF / 1,004,175 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 9 Downloads / 141 Views
ORIGINAL PAPER
Quality-driven tone-mapping operator: a pseudo-exposure fusion-based approach Yang Song1 · Mei Yu2 · Haiyong Xu1 · Gangyi Jiang2 Received: 1 October 2019 / Revised: 1 June 2020 / Accepted: 25 August 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract High dynamic range (HDR) images can present realistic scenes with improved detail in high- and low-brightness regions. Due to their limitations in application, HDR images are often processed by tone-mapping operators (TMOs) to be backwardcompatible with traditional devices. Hence, for a better visual experience, a TMO should naturally preserve the original scene information with image quality as a guideline. With such motivation, we propose a new quality-driven TMO (QdTMO) by using a pseudo-exposure scheme and a local optimal exposed image (LOEI) fusion network. First, a pseudo-exposure scheme is designed to generate richly detailed LOEIs for different brightness regions of the image. Then, scene information in the original HDR image can be naturally preserved by a specifically designed LOEIs fusion network. Finally, the exposure residual energy and brightness naturalness are used to optimize the pseudo-exposure scheme and LOEI fusion for better quality in the resulting tone-mapped image. Experimental results demonstrate that tone-mapped images generated by the proposed QdTMO have better performance than existing TMOs in both subjective and objective evaluations. Keywords High dynamic range · Tone-mapping operators · Pseudo-exposure · LOEI fusion network
1 Introduction From bright sunlight to dim starlight, light conditions in the real world vary tremendously, and intensity levels can span up to nine orders of magnitude [1]. However, due to the limitations of dynamic ranges (usually two orders of magnitude), low dynamic range (LDR) images acquired by traditional imaging devices are often affected by the loss of scene information [2], which greatly reduces the visual experience of users. Recently, with the improvement in sensor and imaging techniques [3], high dynamic range (HDR) imag-
B
Mei Yu [email protected] Yang Song [email protected] Haiyong Xu [email protected] Gangyi Jiang [email protected]
1
College of Science and Technology, Ningbo University, Ningbo 315000, China
2
Faculty of Information Science and Engineering, Ningbo University, Ningbo 315000, China
ing has been applied in industrial [4] and academic fields [5]. Different from LDR imaging, HDR imaging can render a wider light intensity by using more bit depth and thus provide high-quality visual content for users [6]. However, even with the promising background of HDR imaging, HDR display devices still of limited application due to their high price [7]. To improve the applicability of HDR images, they must be converted to be backward-compatible with LDR display devices. Hence, well-performing tone-mapping operators (TMOs) are in high demand and have high application value. Methodologically speaking, TMOs can be mainly divided into the global and the lo
Data Loading...
