Single Image LDR to HDR Conversion using Conditional Diffusion
This addresses the issue of under-/overexposed images in digital imaging for applications requiring realistic scene representation, though it appears incremental as it builds on existing diffusion models.
The paper tackles the problem of converting Low Dynamic Range (LDR) images to High Dynamic Range (HDR) images to recover details from shadows and highlights, achieving results that indicate a simple conditional diffusion-based method can replace complex camera pipeline-based architectures.
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.