Single-image HDR reconstruction or inverse tone mapping (iTM) is a challenging task. In particular, recovering information in over-exposed regions is extremely difficult because details in such regions are almost completely lost. In this paper, we present a deep learning based iTM method that takes advantage of the feature extraction and mapping power of deep convolutional neural networks (CNNs) and uses a lightness prior to modulate the CNN to better exploit observations in the surrounding areas of the over-exposed regions to enhance the quality of HDR image reconstruction. Specifically, we introduce a Hierarchical Synthesis Network (HiSN) for inferring a HDR image from a LDR input and a Lightness Adpative Modulation Network (LAMN) to incorporate the the lightness prior knowledge in the inferring process. The HiSN hierarchically synthesizes the high-brightness component and the low-brightness component of the HDR image whilst the LAMN uses a lightness adaptive mask that separates detail-less saturated bright pixels from well-exposed lower light pixels to enable HiSN to better infer the missing information, particularly in the difficult over-exposed detail-less areas. We present experimental results to demonstrate the effectiveness of the new technique based on quantitative measures and visual comparisons. In addition, we present ablation studies of HiSN and visualization of the activation maps inside LAMN to help gain a deeper understanding of the internal working of the new iTM algorithm and explain why it can achieve much improved performance over state-of-the-art algorithms.

中文翻译：

---

亮度调制深度逆色调映射

单图像 HDR 重建或逆色调映射 (iTM) 是一项具有挑战性的任务。特别是在过度曝光的区域中恢复信息极其困难，因为这些区域的细节几乎完全丢失。在本文中，我们提出了一种基于深度学习的 iTM 方法，该方法利用深度卷积神经网络 (CNN) 的特征提取和映射能力，并在调制 CNN 之前使用亮度，以更好地利用对周围区域的观察。 - 曝光区域以提高 HDR 图像重建的质量。具体来说，我们引入了用于从 LDR 输入推断 HDR 图像的分层合成网络 (HiSN) 和亮度自适应调制网络 (LAMN)，以在推断过程中结合亮度先验知识。HiSN 分层合成 HDR 图像的高亮度分量和低亮度分量，而 LAMN 使用亮度自适应蒙版，将细节较少的饱和明亮像素与曝光良好的低光像素分开，使 HiSN 能够更好地推断缺失的部分信息，特别是在难以过度曝光的无细节区域。我们展示了实验结果，以证明基于定量测量和视觉比较的新技术的有效性。此外，我们展示了 HiSN 的消融研究和 LAMN 内部激活图的可视化，以帮助更深入地了解新 iTM 算法的内部工作，并解释为什么它可以比最先进的算法实现更高的性能.