Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
Journal
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages
1648-1657
Date Issued
2020
Author(s)
Abstract
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. © 2020 IEEE.
Other Subjects
Cameras; Pattern recognition; Pipelines; Camera response functions; Error accumulation; High dynamic range images; Learning-based methods; Nonlinear mappings; Physical constraints; Qualitative experiments; Reconstruction algorithms; Image reconstruction
Type
conference paper