Intrinsic Single-Image HDR Reconstruction

TL;DR

This paper presents a novel approach to single-image HDR reconstruction by decomposing the problem into shading and albedo domains, leveraging a physically-inspired intrinsic model to improve detail recovery in natural scenes.

Contribution

It introduces a new intrinsic domain decomposition method for HDR reconstruction, enabling separate neural networks to better recover luminance and color details from a single LDR image.

Findings

Improved HDR reconstruction quality across diverse images.

Effective separation of shading and albedo enhances detail recovery.

The method outperforms previous single-image HDR techniques.

Abstract

The low dynamic range (LDR) of common cameras fails to capture the rich contrast in natural scenes, resulting in loss of color and details in saturated pixels. Reconstructing the high dynamic range (HDR) of luminance present in the scene from single LDR photographs is an important task with many applications in computational photography and realistic display of images. The HDR reconstruction task aims to infer the lost details using the context present in the scene, requiring neural networks to understand high-level geometric and illumination cues. This makes it challenging for data-driven algorithms to generate accurate and high-resolution results. In this work, we introduce a physically-inspired remodeling of the HDR reconstruction problem in the intrinsic domain. The intrinsic model allows us to train separate networks to extend the dynamic range in the shading domain and to recover lost color details in the albedo domain. We show that dividing the problem into two simpler sub-tasks improves performance in a wide variety of photographs.