Single Image LDR to HDR Conversion using Conditional Diffusion

TL;DR

This paper introduces a novel deep learning framework using conditional diffusion models for converting single LDR images into HDR images, effectively recovering details in shadows and highlights with improved quality.

Contribution

It proposes a new diffusion-based approach with a CNN autoencoder and a novel Exposure Loss for LDR to HDR conversion, outperforming traditional complex pipeline methods.

Findings

Effective recovery of shadow and highlight details.

Outperforms traditional camera pipeline-based architectures.

Demonstrates superior qualitative and quantitative results.

Abstract

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.