We demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Relying on a pre-trained LDR generative diffusion models is vital as, first, there is no sufficiently large HDR image dataset available to re-train them, and, second, even if it was, re-training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called "exposure brackets'', to produce a single HDR image. We operate multiple denoising processes to generate multiple LDR brackets that together form a valid HDR result. The key to making this work is to introduce a consistency term into the diffusion process to couple the brackets such that they agree across the exposure range they share while accounting for possible differences due to the quantization error. We demonstrate state-of-the-art unconditional and conditional or restoration-type (LDR2HDR) generative modeling results, yet in HDR.

翻译：我们展示了利用多个黑盒预训练低动态范围图像扩散模型的协同作用生成高动态范围图像的方法。依赖预训练的低动态范围生成扩散模型至关重要，原因在于：首先，目前缺乏足够大规模的高动态范围图像数据集来重新训练这些模型；其次，即使存在这样的数据集，重新训练这类模型对大多数计算资源预算而言也是不可行的。因此，我们从高动态范围图像采集文献中汲取灵感——传统方法通过融合多张低动态范围图像（称为"曝光括号"）来生成单张高动态范围图像。我们通过运行多个去噪过程来生成多张低动态范围括号图像，这些图像共同构成有效的高动态范围结果。该方法的关键在于向扩散过程中引入一致性约束项，使这些括号图像在共享曝光范围内保持协调一致，同时考虑量化误差可能导致的差异。我们在高动态范围生成建模任务中展示了最先进的无条件生成、条件生成及修复型（低动态范围转高动态范围）生成结果。