High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision. In recent years, there has been a significant advancement in HDR imaging using deep learning (DL). This study conducts a comprehensive and insightful survey and analysis of recent developments in deep HDR imaging methodologies. We hierarchically and structurally group existing deep HDR imaging methods into five categories based on (1) number/domain of input exposures, (2) number of learning tasks, (3) novel sensor data, (4) novel learning strategies, and (5) applications. Importantly, we provide a constructive discussion on each category regarding its potential and challenges. Moreover, we review some crucial aspects of deep HDR imaging, such as datasets and evaluation metrics. Finally, we highlight some open problems and point out future research directions.

翻译：高动态成像(HDR)是一种技术,允许广泛、动态的接触,这对于图像处理、计算机图形和计算机视觉十分重要。近年来,利用深层学习(DL)在《人类发展报告》成像方面取得重大进展。本研究对《人类发展报告》深层成像方法的最新发展进行了全面和有见地的调查和分析。我们分层次和结构将现有的《人类发展报告》深层成像方法分为五类,其基础是:(1) 投入接触的数量/领域,(2) 学习任务的数量,(3) 新型传感器数据,(4) 新的学习战略和(5) 应用。重要的是,我们就每一类别的潜力和挑战进行了建设性的讨论。此外,我们审查了《人类发展报告》深层成像的一些关键方面,如数据集和评价指标。最后,我们强调了一些公开的问题,并指出了未来的研究方向。