Deep Single-Exposure HDR Imaging Approaches
DOI:
https://doi.org/10.54097/hset.v35i.7054Keywords:
Deep Learning; Deep Single-exposure HDR; Neural Network; Neural Sensors.Abstract
The purpose of single-exposure HDR image reconstruction is to recover the missing information in the saturated region of the LDR image, and use neural network to reconstruct the HDR image. In recent years, single-exposure HDR imaging using deep learning (DL) has made significant progress. In this study, the latest development of deep single-exposure HDR imaging method was comprehensively and deeply investigated and analyzed. At present, there are five main methods for deep single-exposure HDR imaging: direct learning from a single LDR image, generating bracketed LDR image stacks, computationally efficient learning, learning camera imaging pipeline, and learning neural sensors. Importantly, this study reviewed the limitations and future work of each category. In addition, this study also discussed the potential and future trends of each category constructively.
Downloads
References
Santos M S, Ren T I, Kalantari N K. Single image HDR reconstruction using a CNN with masked features and perceptual loss[J]. arXiv preprint arXiv:2005.07335, 2020.
Khan Z, Khanna M, Raman S. Fhdr: Hdr image reconstruction from a single ldr image using feedback network [C] //2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE, 2019: 1-5.
Eilertsen G, Kronander J, Denes G, et al. HDR image reconstruction from a single exposure using deep CNNs [J]. ACM transactions on graphics (TOG), 2017, 36(6): 1-15.
Marnerides D, Bashford‐Rogers T, Hatchett J, et al. Expandnet: A deep convolutional neural network for high dynamic range expansion from low dynamic range content[C]//Computer Graphics Forum. 2018, 37(2): 37-49.
Gharbi M, Chen J, Barron J T, et al. Deep bilateral learning for real-time image enhancement[J]. ACM Transactions on Graphics (TOG), 2017, 36(4): 1-12.
Moriwaki K, Yoshihashi R, Kawakami R, et al. Hybrid loss for learning single-image-based HDR reconstruction[J]. arXiv preprint arXiv:1812.07134, 2018.
Kinoshita Y, Kiya H. ITM-Net: Deep inverse tone mapping using novel loss function considering tone mapping operator[J]. IEEE Access, 2019, 7: 73555-73563.
Endo Y, Kanamori Y, Mitani J. Deep reverse tone mapping[J]. ACM Trans. Graph., 2017, 36(6): 177:1-177:10.
Lee S, An G H, Kang S J. Deep chain hdri: Reconstructing a high dynamic range image from a single low dynamic range image[J]. IEEE Access, 2018, 6: 49913-49924.
Lee S, An G H, Kang S J. Deep recursive hdri: Inverse tone mapping using generative adversarial networks[C]//proceedings of the European Conference on Computer Vision (ECCV). 2018: 596-611.
Kim J, Lee S, Kang S J. End-to-end differentiable learning to hdr image synthesis for multi-exposure images[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021, 35(2): 1780-1788.
Cai J, Gu S, Zhang L. Learning a deep single image contrast enhancer from multi-exposure images[J]. IEEE Transactions on Image Processing, 2018, 27(4): 2049-2062.
An V G, Lee C. Single-shot high dynamic range imaging via deep convolutional neural network[C]//2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 2017: 1768-1772.
Yang X, Xu K, Song Y, et al. Image correction via deep reciprocating HDR transformation [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 1798-1807.
Zeng H, Cai J, Li L, et al. Learning image-adaptive 3d lookup tables for high performance photo enhancement in real-time[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.
Liu Y L, Lai W S, Chen Y S, et al. Single-image HDR reconstruction by learning to reverse the camera pipeline [C] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1651-1660.
Metzler C A, Ikoma H, Peng Y, et al. Deep optics for single-shot high-dynamic-range imaging [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1375-1385.
Alghamdi M M, Fu Q, Thabet A K, et al. Reconfigurable snapshot HDR imaging using coded masks and inception network [J]. 2019.
Martel J N P, Mueller L K, Carey S J, et al. Neural sensors: Learning pixel exposures for HDR imaging and video compressive sensing with programmable sensors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(7): 1642-1653.
Zhang J, Lalonde J F. Learning high dynamic range from outdoor panoramas[C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 4519-4528.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
