Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior

TL;DR

Sagiri introduces a two-stage HDR image enhancement method combining color mapping with a diffusion prior to restore details lost in low dynamic range images, outperforming existing techniques.

Contribution

The paper presents a novel two-stage approach that integrates a diffusion prior for content generation in HDR enhancement, surpassing traditional methods in detail restoration.

Findings

Significant improvement in image detail and quality.

Effective restoration of dynamic range extremes.

Versatile plug-and-play diffusion module.

Abstract

Capturing High Dynamic Range (HDR) scenery using 8-bit cameras often suffers from over-/underexposure, loss of fine details due to low bit-depth compression, skewed color distributions, and strong noise in dark areas. Traditional LDR image enhancement methods primarily focus on color mapping, which enhances the visual representation by expanding the image's color range and adjusting the brightness. However, these approaches fail to effectively restore content in dynamic range extremes, which are regions with pixel values close to 0 or 255. To address the full scope of challenges in HDR imaging and surpass the limitations of current models, we propose a novel two-stage approach. The first stage maps the color and brightness to an appropriate range while keeping the existing details, and the second stage utilizes a diffusion prior to generate content in dynamic range extremes lost during capture. This generative refinement module can also be used as a plug-and-play module to enhance and complement existing LDR enhancement models. The proposed method markedly improves the quality and details of LDR images, demonstrating superior performance through rigorous experimental validation. The project page is at https://sagiri0208.github.io