Deep learning is commonly used to reconstruct HDR images from LDR images. LDR stack-based methods are used for single-image HDR reconstruction, generating an HDR image from a deep learning-generated LDR stack. However, current methods generate the stack with predetermined exposure values (EVs), which may limit the quality of HDR reconstruction. To address this, we propose the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training. Our approach generates a continuous stack with more images containing diverse EVs, significantly improving HDR reconstruction. We use a cycle training strategy to supervise the model in generating continuous EV LDR images without corresponding ground truths. Our CEVR model outperforms existing methods, as demonstrated by experimental results.

翻译：深度学习常用于从低动态范围图像重建高动态范围图像。基于LDR堆叠的方法被用于单图像HDR重建，即从深度学习生成的LDR堆叠中生成HDR图像。然而，现有方法以预定曝光值生成堆叠，这限制了HDR重建的质量。为解决此问题，我们提出连续曝光值表示（CEVR），该表示利用隐式函数生成任意曝光值（包括训练中未见过的曝光值）的LDR图像。我们的方法通过生成包含更多多样化曝光值图像的连续堆叠，显著提升了HDR重建效果。我们采用循环训练策略监督模型生成连续曝光值LDR图像，且无需对应真实标注。实验结果表明，我们的CEVR模型优于现有方法。