Generating a high-quality High Dynamic Range (HDR) image from dynamic scenes has recently been extensively studied by exploiting Deep Neural Networks (DNNs). Most DNNs-based methods require a large amount of training data with ground truth, requiring tedious and time-consuming work. Few-shot HDR imaging aims to generate satisfactory images with limited data. However, it is difficult for modern DNNs to avoid overfitting when trained on only a few images. In this work, we propose a novel semi-supervised approach to realize few-shot HDR imaging via two stages of training, called SSHDR. Unlikely previous methods, directly recovering content and removing ghosts simultaneously, which is hard to achieve optimum, we first generate content of saturated regions with a self-supervised mechanism and then address ghosts via an iterative semi-supervised learning framework. Concretely, considering that saturated regions can be regarded as masking Low Dynamic Range (LDR) input regions, we design a Saturated Mask AutoEncoder (SMAE) to learn a robust feature representation and reconstruct a non-saturated HDR image. We also propose an adaptive pseudo-label selection strategy to pick high-quality HDR pseudo-labels in the second stage to avoid the effect of mislabeled samples. Experiments demonstrate that SSHDR outperforms state-of-the-art methods quantitatively and qualitatively within and across different datasets, achieving appealing HDR visualization with few labeled samples.

翻译：从动态场景生成高质量高动态范围图像近年来通过深度神经网络得到了广泛研究。大多数基于深度神经网络的方法需要大量带有真实标签的训练数据，这要求繁琐且耗时的工作。少样本HDR成像旨在利用有限数据生成令人满意的图像。然而，现代深度神经网络在仅由少量图像训练时难以避免过拟合。本文提出一种新颖的半监督方法，通过两阶段训练实现少样本HDR成像，称为SSHDR。与先前同时直接恢复内容和去除鬼影（难以达到最优）的方法不同，我们首先通过自监督机制生成饱和区域内容，然后通过迭代半监督学习框架处理鬼影。具体而言，考虑到饱和区域可视为对低动态范围输入区域的掩蔽，我们设计了一种饱和掩码自编码器来学习鲁棒特征表示并重建非饱和HDR图像。我们还提出一种自适应伪标签选择策略，在第二阶段挑选高质量HDR伪标签，以避免错误标记样本的影响。实验表明，SSHDR在数据集内部和跨数据集上均超越了现有最优方法的定量和定性结果，在少量标注样本下实现了令人满意的HDR可视化效果。