The most recent High Dynamic Range (HDR) standard, HDR10+, achieves good picture quality by incorporating dynamic metadata that carry frame-by-frame information for tone mapping while most HDR standards use static tone mapping curves that apply across the entire video. Since it is laborious to acquire hand-crafted best-fitting tone mapping curve for each frame, there have been attempts to derive the curves from input images. This paper proposes the neural network framework that generates tone mapping on a frame-by-frame basis. Although a number of successful tone mapping operators (TMOs) have been proposed over the years, evaluation of tone mapped images still remains a challenging topic. We define an objective measure to evaluate tone mapping based on Non-Reference Image Quality Assessment (NR-IQA). Experiments show that the framework produces good tone mapping curves and makes the video more vivid and colorful.

https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11137/111370S/A-NR-IQA-based-deep-neural-network-for-tone-mapping/10.1117/12.2528617.full?SSO=1