Digital imaging aims to replicate realistic scenes, but Low Dynamic Range (LDR) cameras cannot represent the wide dynamic range of real scenes, resulting in under-/overexposed images. This paper presents a deep learning-based approach for recovering intricate details from shadows and highlights while reconstructing High Dynamic Range (HDR) images. We formulate the problem as an image-to-image (I2I) translation task and propose a conditional Denoising Diffusion Probabilistic Model (DDPM) based framework using classifier-free guidance. We incorporate a deep CNN-based autoencoder in our proposed framework to enhance the quality of the latent representation of the input LDR image used for conditioning. Moreover, we introduce a new loss function for LDR-HDR translation tasks, termed Exposure Loss. This loss helps direct gradients in the opposite direction of the saturation, further improving the results' quality. By conducting comprehensive quantitative and qualitative experiments, we have effectively demonstrated the proficiency of our proposed method. The results indicate that a simple conditional diffusion-based method can replace the complex camera pipeline-based architectures.

翻译：数字成像旨在再现真实场景，但低动态范围（LDR）相机无法呈现真实场景的宽广动态范围，从而产生欠曝光或过曝光的图像。本文提出了一种基于深度学习的方法，用于从阴影和高光区域恢复精细细节，同时重建高动态范围（HDR）图像。我们将该问题建模为图像到图像（I2I）翻译任务，并基于无分类器引导，提出了一种基于条件去噪扩散概率模型（DDPM）的框架。我们在所提出的框架中引入了深度CNN自编码器，以增强用于条件化的输入LDR图像潜在表示的质量。此外，我们针对LDR-HDR翻译任务提出了一种新的损失函数，称为曝光损失。该损失有助于将梯度导向饱和度的相反方向，从而进一步提升结果的质量。通过全面的定量和定性实验，我们有效证明了所提出方法的有效性。结果表明，一种简单的基于条件扩散的方法可以替代复杂的相机流水线架构。