Journal
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Volume -, Issue -, Pages 1648-1657Publisher
IEEE
DOI: 10.1109/CVPR42600.2020.00172
Keywords
-
Categories
Funding
- NSF CAREER [1149783]
- NSF CRII [1755785]
- MOST [109-2634-F-002-032]
- MediaTek Inc.
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1755785] Funding Source: National Science Foundation
Ask authors/readers for more resources
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 HDR-to-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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available