Intrinsic Image Decomposition via Structure-Preserving Image Smoothing and Material Recognition

Decoupling shading and reflectance from complex scene-images is a long-standing problem in computer vision. We introduce a framework for decomposing an image into the product of an illumination component and a reflectance component. Due to the ill-posed nature of the problem, prior information on sh...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2016-12, Vol.11 (12), p.e0166772-e0166772
Main Authors: Nadian-Ghomsheh, Ali, Hasanian, Yassin, Navi, Keyvan
Format: Article
Language:English
Subjects:
Algorithms
Analysis
Chromaticity
Colorization
Computer science
Computer vision
Datasets
Decomposition
Decoupling
Engineering and Technology
Ill posed problems
Ill-posed problems (mathematics)
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image processing
Image quality
Imaging, Three-Dimensional - methods
Methods
Object recognition
Pattern Recognition, Automated - methods
Physical Sciences
Pixels
Quantitative analysis
Reflectance
Research and Analysis Methods
Shading
Sparsity
Texture
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Decoupling shading and reflectance from complex scene-images is a long-standing problem in computer vision. We introduce a framework for decomposing an image into the product of an illumination component and a reflectance component. Due to the ill-posed nature of the problem, prior information on shading and reflectance is mandatory. The proposed method adopts the premise that pixels in a region with similar chromaticity values should have the same reflectance. This assumption was used to minimize the l2 norm of the local per-pixel reflectance gradients to extract the shading and reflectance components. To obtain smooth chromatic regions, texture was treated in a new style. Texture was removed in the first step of the algorithm and the smooth image was processed for intrinsic decomposition. In the final step, texture details were added to the intrinsic components based on the material of each pixel. In addition, user-assistance was used to further refine the results. The qualitative and quantitative evaluation on the MIT intrinsic dataset indicated that the quality of intrinsic image decomposition was improved in comparison with previous methods.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0166772