Item

Abstract

We demonstrate generating high-dynamic range (HDR) images using the concerted
action of multiple black-box, pre-trained low-dynamic range (LDR) image
diffusion models. Common diffusion models are not HDR 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 "brackets", to produce a single
HDR image. We operate multiple denoising processes to generate multiple LDR
brackets that together form a valid HDR result. To this end, we introduce an
exposure consistency term into the diffusion process to couple the brackets
such that they agree across the exposure range they share. We demonstrate HDR
versions of state-of-the-art unconditional and conditional as well as
restoration-type (LDR2HDR) generative modeling.