Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency

TL;DR

This paper introduces a self-supervised neural network for intrinsic image decomposition that emphasizes reflectance consistency across different illumination conditions, improving decomposition accuracy.

Contribution

It proposes a novel network considering reflectance consistency using a color-illuminant model and self-supervised training with simulated illumination variations.

Findings

Effective decomposition into reflectance and shading components.

Outperforms existing methods in reflectance consistency.

Self-supervised training enables robust learning without extensive labeled data.

Abstract

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.