In this paper, we propose a novel inverse tone mapping network, called “iTM-Net.” For training iTM-Net, we also propose a novel loss function that considers the non-linear relation between low dynamic range (LDR) and high dynamic range (HDR) images. For inverse tone mapping with convolutional neural networks (CNNs), we first point out that training CNNs with a standard loss function causes a problem due to the non-linear relation between the LDR and HDR images. To overcome the problem, the novel loss function non-linearly tone-maps target HDR images into LDR ones on the basis of a tone mapping operator, and the distance between the tone-mapped images and predicted ones are then calculated. The proposed loss function enables us not only to normalize the HDR images but also to reduce the non-linear relation between LDR and HDR ones. The experimental results show that the HDR images predicted by the proposed iTM-Net have higher-quality than the HDR ones predicted by conventional inverse tone mapping methods, including the state of the art, in terms of both HDR-VDP-2.2 and PU encoding + MS-SSIM. In addition, compared with loss functions that do not consider the non-linear relation, the proposed loss function is shown to improve the performance of CNNs.
Codes are available on GitHub.
When you use this implementation for your research work, please cite the paper.
Yuma KINOSHITA and Hitoshi KIYA,“iTM-Net: Deep Inverse Tone Mapping Using Novel Loss Function Considering Tone Mapping Operator,”IEEE Access, vol.7, no.1, pp.73555-73563, May 2019.@article{kinoshita2019itmnet,author = {Kinoshita, Yuma and Kiya, Hitoshi},doi = {10.1109/ACCESS.2019.2919296},issn = {2169-3536},journal = {IEEE Access},volume = {7},number = {1},pages = {73555--73563},title = {{iTM-Net: Deep Inverse Tone Mapping Using Novel Loss Function Considering Tone Mapping Operator}},url = {https://ieeexplore.ieee.org/document/8723346/},month = {May},year = {2019}}