Invariant Descriptors for Intrinsic Reflectance Optimization

TL;DR

This paper introduces illumination invariant color ratio descriptors into a dense CRF framework to improve the accuracy and robustness of intrinsic reflectance decomposition in images, addressing the ill-posed nature of the problem.

Contribution

It proposes a physics-based, learning-free method that incorporates color ratios as invariant descriptors into the CRF model for better intrinsic image decomposition.

Findings

Enhanced reflectance decomposition accuracy

More robust to illumination variations

Improved results over previous models

Abstract

Intrinsic image decomposition aims to factorize an image into albedo (reflectance) and shading (illumination) sub-components. Being ill-posed and under-constrained, it is a very challenging computer vision problem. There are infinite pairs of reflectance and shading images that can reconstruct the same input. To address the problem, Intrinsic Images in the Wild provides an optimization framework based on a dense conditional random field (CRF) formulation that considers long-range material relations. We improve upon their model by introducing illumination invariant image descriptors: color ratios. The color ratios and the reflectance intrinsic are both invariant to illumination and thus are highly correlated. Through detailed experiments, we provide ways to inject the color ratios into the dense CRF optimization. Our approach is physics-based, learning-free and leads to more accurate and robust reflectance decompositions.