Intrinsic Image Decomposition using
Structure-Texture Separation and Surface Normals

Junho Jeon
POSTECH

Sunghyun Cho
Adobe Research

Xin Tong
Miscrosoft Research Asia

Seungyong Lee
POSTECH

European Conference on Computer Vision (ECCV 2014), September 2014.

Abstract

While intrinsic image decomposition has been studied extensively during the past a few decades, it is a still challenging problem. This is partly because commonly used constraints on shading and reflectance are often too restrictive to capture an important property of natural images, i.e., rich textures. In this paper, we propose a novel image model for handling textures in intrinsic image decomposition, which enables us to produce high quality results even with simple constraints. We also propose a novel constraint based on surface normals, which can be obtained from an RGB-D image. Assuming Lambertian surfaces, we formulate the constraint based on a locally linear embedding framework to promote local and global consistency on the shading layer. We demonstrate that combining the novel texture-aware image model and the novel constraint based on surface normals can produce superior intrinsic image decomposition results to existing approaches.