Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) input image is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of camera sensors. In contrast to existing learning-based methods, our core idea is to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDRto-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We then propose to learn three specialized CNNs to reverse these steps. By decomposing the problem into specific sub-tasks, we impose effective physical constraints to facilitate the training of individual sub-networks. Finally, we jointly fine-tune the entire model end-to-end to reduce error accumulation. With extensive quantitative and qualitative experiments on diverse image datasets, we demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms.

@inproceedings{liu2020single,
    author    = {Liu, Yu-Lun and Lai, Wei-Sheng and Chen, Yu-Sheng and Kao, Yi-Lung and Yang, Ming-Hsuan and Chuang, Yung-Yu and Huang, Jia-Bin}, 
    title     = {Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline}, 
    booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
    year      = {2020}
}

• • HDR image reconstruction from a single exposure using deep CNNs, SIGGRAPH Asia, 2017.
• • Deep reverse tone mapping, SIGGRAPH Asia, 2017.
• • ExpandNet: A deep convolutional neural network for high dynamic range expansion from low dynamic range content, Eurographics, 2018.