An Optical Physics Inspired CNN Approach for Intrinsic Image Decomposition

Abstract

Intrinsic ImageDecomposition is an open problem of generating the constituents of an image. Generating reflectance and shading from a single image is a challenging task specifically when there is no ground truth. There is a lack of unsupervised learning approaches for decomposing an image into reflectance and shading using a single image. We propose a neural network architecture capable of this decomposition using physics-based parameters derived from the image. Through experimental results, we show that (a) the proposed methodology outperforms the existing deep learningbased IID techniques and (b) the derived parameters improve the efficacy significantly. We conclude with a closer analysis of the results (numerical and example images) showing several avenues for improvement. Index Termsintrinsic image decomposition (IID), convolutional neural networks (CNN), Phong model.