End-to-End Deep HDR Imaging with Large Foreground Motions
End-to-End Deep HDR Imaging with Large Foreground Motions
复制标题
DOI：
--
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Shangzhe Wu;Jiarui Xu;Yu-Wing Tai;Chi-Keung Tang
中科院分区：
文献类型：
--
作者：
Shangzhe Wu;Jiarui Xu;Yu-Wing Tai;Chi-Keung Tang
本文提出了第一个端到端深度框架，用于具有大规模前景运动的动态场景的高动态范围（HDR）成像。在最先进的深度HDR成像中，例如[13]，该问题被公式化为图像合成问题，首先使用由于遮挡和大运动而仍然容易出错的光流对准输入图像。在我们的端到端方法中，HDR成像被公式化为图像平移问题，并且不使用光流。此外，我们简单的翻译网络可以在存在完全遮挡、饱和和曝光不足的情况下自动产生合理的HDR细节，否则通过传统优化方法几乎不可能恢复这些细节。我们进行了广泛的定性和定量比较，以表明我们的端到端HDR方法产生了出色的结果，与现有的最先进的方法相比，颜色伪影和几何失真显着减少。
This paper proposes the first end-to-end deep framework for high dynamic range (HDR) imaging of dynamic scenes with large-scale foreground motions. In state-of-the-art deep HDR imaging such as [13], the problem is formulated as an image composition problem, by first aligning input images using optical flows which are still error-prone due to occlusion and large motions. In our end-to-end approach, HDR imaging is formulated as an image translation problem and no optical flows are used. Moreover, our simple translation network can automatically hallucinate plausible HDR details in the presence of total occlusion, saturation and under-exposure, which are otherwise almost impossible to recover by conventional optimization approaches. We perform extensive qualitative and quantitative comparisons to show that our end-to-end HDR approach produces excellent results where color artifacts and geometry distortion are significantly reduced compared with existing state-ofthe-art methods.