Light mixture intrinsic image decomposition based on a single RGB-D image

Abstract

We propose a novel intrinsic image decomposition method based on a single RGB-D image. We first separate the shading image into an illumination color component, a distant shading component and a local shading component, inducing a novel intrinsic image model that can encode color and spatial variation of scene illumination. Unlike previous methods, which assume illumination color is white, our light mixture model encodes scene illumination with two different light types, and an automatical strategy is proposed to calculate the color of the two light types. We also adopt physical-based illumination prior to infer the distant shading component. To do so, we firstly recover the illumination distribution of the distant light sources through solving a system of linear equations with sparse and non-negative constraints. Then, the recovered illumination is used to synthesize a coarse distant shading image jointly with the depth map. Later, the synthetic image is employed as an additional constraint of distant shading component. To reduce noise disturbance from the synthetic distant shading image, a novel sampling strategy was proposed. Finally, we consider the similarity of material locally and globally, which gives reliable constraints to the reflectance component. Experimental results demonstrate the validity and flexibility of our approach.