Non-local Intrinsic Decomposition with Near-infrared Priors

Ziang CHENG, Yinqiang ZHENG, Shaodi YOU, Imari SATO

Abstract:

Intrinsic image decomposition is a highly underconstrained problem that has been extensively studied by
computer vision researchers. Previous methods impose additional constraints by exploiting either empirical or datadriven priors. In this paper, we revisit intrinsic image decomposition with the aid of near-infrared (NIR) imagery.
We show that NIR band is considerably less sensitive to
textures and can be exploited to reduce ambiguity caused
by reflectance variation, promoting a simple yet powerful
prior for shading smoothness. With this observation, we
formulate intrinsic decomposition as an energy minimisation problem. Unlike existing methods, our energy formulation decouples reflectance and shading estimation, into
a convex local shading component based on NIR-RGB image pair, and a reflectance component that encourages reflectance homogeneity both locally and globally. We further
show the minimisation process can be approximated by a
series of multi-dimensional convolutions, each within linear
time complexity. To validate the proposed algorithm, a NIRRGB dataset is captured over real-world objects, where our
NIR-assisted approach demonstrates superiority over RGB
methods.