Intrinsic Image Decomposition Using Structure-Texture Separation and Surface Normals

  • Junho Jeon
  • Sunghyun Cho
  • Xin Tong
  • Seungyong Lee
Conference paper

DOI: 10.1007/978-3-319-10584-0_15

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8695)
Cite this paper as:
Jeon J., Cho S., Tong X., Lee S. (2014) Intrinsic Image Decomposition Using Structure-Texture Separation and Surface Normals. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8695. Springer, Cham

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.

Keywords

intrinsic image decomposition structure-texture separation RGB-D image 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

978-3-319-10584-0_15_MOESM1_ESM.pdf (10.5 mb)
Electronic Supplementary Material (PDF 10,709 KB)

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Junho Jeon
    • 1
  • Sunghyun Cho
    • 2
  • Xin Tong
    • 3
  • Seungyong Lee
    • 1
  1. 1.POSTECHKorea
  2. 2.Adobe ResearchKorea
  3. 3.Microsoft Research AsiaChina

Personalised recommendations