Deep HDR estimation with generative detail reconstruction

We present qualitative and quantitative comparisons with existing techniques where our method achieves state-of-the-art performance.

We study the problem of High Dynamic Range (HDR) image reconstruction from a Standard Dynamic Range (SDR) input with potential clipping artifacts. Instead of building a direct model that maps from SDR to HDR images as in previous work, we decompose an input SDR image into a base (low frequency) and detail layer (high frequency), and treat reconstructing these two layers as two separate problems. We propose a novel architecture that comprises individual components specially designed to handle both tasks. Specifically, our base layer reconstruction component recovers low frequency content and remaps the color gamut of the input SDR, whereas our detail layer reconstruction component, which is inspired by prior work in image inpainting, hallucinates missing texture information. The output HDR prediction is produced by a final refinement stage. We present qualitative and quantitative comparisons with existing techniques where our method achieves state-of-the-art performance.