APSIPA Transactions on Signal and Information Processing > Vol 11 > Issue 1

Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency

Yuma Kinoshita, Tokyo Metropolitan University, Japan, ykinoshita@tmu.ac.jp , Hitoshi Kiya, Tokyo Metropolitan University, Japan
Suggested Citation
Yuma Kinoshita and Hitoshi Kiya (2022), "Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency", APSIPA Transactions on Signal and Information Processing: Vol. 11: No. 1, e3. http://dx.doi.org/10.1561/116.00000027

Publication Date: 05 Apr 2022
© 2022 Y. Kinoshita and H. Kiya
Intrinsic image decompositionRetinexSelf supervised learningMulti exposure images


Open Access

This is published under the terms of CC BY-NC.

Downloaded: 1325 times

In this article:
Proposed Intrinsic Image Decomposition Network 
Training Proposed Network in Self-supervised Manner 


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.



APSIPA Transactions on Signal and Information Processing Deep Neural Networks: Representation, Interpretation, and Applications: Articles Overview
See the other articles that are part of this special issue.