Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency
This work addresses the problem of intrinsic image decomposition for computer vision applications, but it is incremental as it builds on existing consistency frameworks.
The paper tackles intrinsic image decomposition by proposing a self-supervised network that enforces reflectance consistency using a color-illuminant model and losses from varied illumination conditions, achieving decomposition into reflectance and shading components.
We propose a novel intrinsic image decomposition network considering reflectance consistency. Intrinsic image decomposition aims to decompose an image into illumination-invariant and illumination-variant components, referred to as ``reflectance'' and ``shading,'' respectively. Although there are three consistencies that the reflectance and shading should satisfy, most conventional work does not sufficiently account for consistency with respect to reflectance, owing to the use of a white-illuminant decomposition model and the lack of training images capturing the same objects under various illumination-brightness and -color conditions. For this reason, the three consistencies are considered in the proposed network by using a color-illuminant model and training the network with losses calculated from images taken under various illumination conditions. In addition, the proposed network can be trained in a self-supervised manner because various illumination conditions can easily be simulated. Experimental results show that our network can decompose images into reflectance and shading components.