Invariant Descriptors for Intrinsic Reflectance Optimization
This incremental improvement addresses intrinsic image decomposition for computer vision applications, enhancing reflectance estimation in uncontrolled environments.
The paper tackles the ill-posed problem of intrinsic image decomposition by introducing illumination-invariant color ratios into a dense CRF optimization framework, resulting in more accurate and robust reflectance decompositions without learning.
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.