Intrinsic Image Decomposition
Using Structure-Texture Separation and Surface Normals

Junho Jeon1 Sunghyun Cho2 Xin Tong3 Seungyong Lee1
1POSTECH 2Adobe Research 3Microsoft Research Asia

Proc. 13th European Conference on Computer Vision (ECCV 2014)


Input RGB image Input depth image
 
Result reflectance Result shading

Abstract

While intrinsic image decomposition has been studied extensively during the past a few decades, it is still a 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 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 surface normal based constraint can produce superior results to existing approaches.

Paper
PDF(6.98MB)
Supp. Material
PDF(10.4MB)
Code
Download

BibTex

@inproceedings{jeon_eccv2014,
  author = {Junho Jeon and Sunghyun Cho and Xin Tong and Seungyong Lee},
  title = {Intrinsic Image Decomposition Using Structure-Texture Separation and Surface Normals},
  booktitle = {Proc. 13th European Conference on Computer Vision (ECCV 2014)},
  year = {2014}
}


Coupe: Open Source Photo Enhancement Library