Intrinsic Single-Image HDR Reconstruction
This work addresses the challenge of HDR reconstruction for computational photography and realistic image display, offering an incremental improvement by dividing the problem into simpler sub-tasks.
The paper tackles the problem of reconstructing high dynamic range (HDR) from single low dynamic range (LDR) photographs, which often lose color and details in saturated pixels, by introducing a physically-inspired intrinsic domain approach that trains separate networks for shading and albedo to improve performance across various photographs.
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.