HDR image reconstruction from a single exposure using deep CNNs
ACM Transactions on Graphics
MetadataShow full item record
Eilertsen, G., Kronander, J., Denes, G., Mantiuk, R., & Unger, J. (2017). HDR image reconstruction from a single exposure using deep CNNs. ACM Transactions on Graphics, 36 (6)https://doi.org/10.1145/3130800.3130816
Camera sensors can only capture a limited range of luminance simultane- ously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combined. In this paper we address the problem of predicting information that have been lost in saturated image ar- eas, in order to enable HDR reconstruction from a single exposure.We show that this problem is well-suited for deep learning algorithms, and propose a deep convolutional neural network (CNN) that is specifically designed taking into account the challenges in predicting HDR values. To train the CNN we gather a large dataset of HDR images, which we augment by simulating sensor saturation for a range of cameras. To further boost robustness, we pre-train the CNN on a simulated HDR dataset created from a subset of the MIT Places database.We demonstrate that our approach can reconstruct high-resolution visually convincing HDR results in a wide range of situa- tions, and that it generalizes well to reconstruction of images captured with arbitrary and low-end cameras that use unknown camera response func- tions and post-processing. Furthermore, we compare to existing methods for HDR expansion, and show high quality results also for image based lighting. Finally, we evaluate the results in a subjective experiment performed on an HDR display. This shows that the reconstructed HDR images are visually convincing, with large improvements as compared to existing methods.
External DOI: https://doi.org/10.1145/3130800.3130816
This record's URL: https://www.repository.cam.ac.uk/handle/1810/277485