Shadow Patching: Guided Image Completion for Shadow Removal

Abstract

Removing unwanted shadows is a common need in photo editing software. Previous methods handle some shadows well but perform poorly in cases with severe degradation (darker shadowing) because they rely on directly restoring the degraded data in the shadowed region. Image-completion algorithms can completely replace severely degraded shadowed regions, and perform well with smaller-scale textures, but often fail to reproduce larger-scale macrostructure that may still be visible in the shadowed region. This paper provides a general framework that leverages degraded (in this case shadowed) data in a region to guide image completion by extending the objective function commonly used in current state-of-the-art energy-minimization methods for image completion to include not only visual realism but consistency with the original degraded content. This approach achieves realistic-looking shadow removal even in cases of severe degradation where precise recovery of the unshadowed content may not be possible. Although not demonstrated here, the generality of the approach potentially allows it to be extended to other types of localized degradation.