Tone mapping is one of the main techniques to convert high-dynamic range (HDR) images into low-dynamic range (LDR) images. We propose to use a variant of generative adversarial networks to adaptively tone map images. We designed a conditional adversarial generative network composed of a U-Net generator and patchGAN discriminator to adaptively convert HDR images into LDR images. We extended previous work to include additional metrics such as tone-mapped image quality index (TMQI), structural similarity index measure, Fréchet inception distance, and perceptual path length. In addition, we applied face detection on the Kalantari dataset and showed that our proposed adversarial tone mapping operator generates the best LDR image for the detection of faces. One of our training schemes, trained via 256 × 256 resolution HDR–LDR image pairs, results in a model that can generate high TMQI low-resolution 256 × 256 and high-resolution 1024 × 2048 LDR images. Given 1024 × 2048 resolution HDR images, the TMQI of the generated LDR images reaches a value of 0.90, which outperforms all other contemporary tone mapping operators.

中文翻译：

---

对抗性和自适应色调映射算子：多方案生成和多度量评估

色调映射是将高动态范围 (HDR) 图像转换为低动态范围 (LDR) 图像的主要技术之一。我们建议使用生成对抗网络的变体来自适应地色调映射图像。我们设计了一个由 U-Net 生成器和 patchGAN 鉴别器组成的条件对抗生成网络，以自适应地将 HDR 图像转换为 LDR 图像。我们扩展了之前的工作以包括其他指标，例如色调映射图像质量指数 (TMQI)、结构相似性指数测量、Fréchet 初始距离和感知路径长度。此外，我们在 Kalantari 数据集上应用了人脸检测，并表明我们提出的对抗性色调映射算子生成了用于检测人脸的最佳 LDR 图像。我们的训练方案之一，通过 256 × 256 分辨率的 HDR-LDR 图像对进行训练，导致模型可以生成高TMQI 低分辨率256 × 256 和高分辨率1024 × 2048 LDR 图像。给定 1024 × 2048 分辨率的 HDR 图像，生成的 LDR 图像的 TQI 值达到 0.90，优于所有其他当代色调映射算子。