Abstract
Currently published tone mapping operators (TMO) are often evaluated on a very limited test set of high dynamic range (HDR) images. Thus, the resulting performance index is highly subject to extensive hyperparameter tuning, and many TMOs exhibit sub-optimal performance when tested on a broader spectrum of HDR images. This indicates that there are deficiencies in the generalizable applicability of these techniques. Finally, it is a challenge developing parameter-free tone mapping operators using data-hungry advanced deep learning methods due to the paucity of large scale HDR datasets. In this paper, these issues are addressed through the following contributions: a) a large scale HDR image benchmark dataset (LVZ-HDR dataset) with multiple variations in sceneries and lighting conditions is created to enable performance evaluation of TMOs across a diverse conditions and scenes that will also contribute to facilitate the development of more robust TMOs using state-of-the-art deep learning methods; b) a deep learning-based tone mapping operator (TMO-Net) is presented, which offers an efficient and parameter-free method capable of generalizing effectively across a wider spectrum of HDR content; c) finally, a comparative analysis, and performance benchmarking of 19 state-of-the-art TMOs on the new LVZ-HDR dataset are presented. Standard metrics including the Tone Mapping Quality Index (TMQI), Feature Similarity Index for Tone Mapped images (FSITM), and Natural Image Quality Evaluator (NIQE) are used to qualitatively evaluate the performance index of the benchmarked TMOs. Experimental results demonstrate that the proposed TMO-Net qualitatively and quantitatively outperforms current state-of-the-art TMOs.
Highlights
Despite 20 years of research and dozens of proposed algorithms, tone-mapping for high dynamic range images remains a difficult problem
The lack of a standard large-scale HDR dataset makes it difficult to develop and compare deep-learning algorithms for tone mapping. This lack of a standard dataset makes it harder to quantitatively benchmark traditional TMOs and evaluate progress in the field. This work addresses these with the following contributions: 1) First, a large scale HDR image benchmark dataset (LVZ-HDR dataset) with high variability in sceneries and lighting conditions is created to promote performance evaluation of TMOs, and to facilitate the development of more robust and more generalizable TMOs using state-of-the-art deep learning methods
The downside of deep neural nets approach to solving a problem is that they are data-hungry methods and require thousands of image samples and equivalent ground truth. This means that to properly train a generative adversarial networks (GANs)-based model to perform automatic tone mapping operation on input images as we are trying to accomplish in this paper, there is a need to gather a dataset with thousands of HDR images, and the corresponding ground truth tone mapped images
Summary
Despite 20 years of research and dozens of proposed algorithms, tone-mapping for high dynamic range images remains a difficult problem. The lack of a standard large-scale HDR dataset makes it difficult to develop and compare deep-learning algorithms for tone mapping This lack of a standard dataset makes it harder to quantitatively benchmark traditional TMOs and evaluate progress in the field. This work addresses these with the following contributions: 1) First, a large scale HDR image benchmark dataset (LVZ-HDR dataset) with high variability in sceneries and lighting conditions is created to promote performance evaluation of TMOs, and to facilitate the development of more robust and more generalizable TMOs using state-of-the-art deep learning methods. 2) Second, a deep learning-based tone mapping operator (TMO-Net) is proposed This operator is efficient and parameter-free and performs well across a wide range of HDR scenes.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
