DocumentCode
3329858
Title
Non-parametric Filtering for Geometric Detail Extraction and Material Representation
Author
Zicheng Liao ; Rock, Jason ; Yang Wang ; Forsyth, David
fYear
2013
fDate
23-28 June 2013
Firstpage
963
Lastpage
970
Abstract
Geometric detail is a universal phenomenon in real world objects. It is an important component in object modeling, but not accounted for in current intrinsic image works. In this work, we explore using a non-parametric method to separate geometric detail from intrinsic image components. We further decompose an image as albedo * (coarse-scale shading + shading detail). Our decomposition offers quantitative improvement in albedo recovery and material classification. Our method also enables interesting image editing activities, including bump removal, geometric detail smoothing/enhancement and material transfer.
Keywords
computational geometry; image classification; image enhancement; nonparametric statistics; smoothing methods; albedo recovery; bump removal; coarse-scale shading; geometric detail enhancement; geometric detail extraction; geometric detail smoothing; image editing activity; intrinsic image components; intrinsic image works; material classification; material representation; material transfer; nonparametric filtering; nonparametric method; object modeling; quantitative improvement; real world objects; shading detail; Dictionaries; Geometry; Image color analysis; Image edge detection; Laboratories; Lighting; Materials; Geometric detail; intrinsic image decomposition; material representation;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Conference_Location
Portland, OR
ISSN
1063-6919
Type
conf
DOI
10.1109/CVPR.2013.129
Filename
6618973
Link To Document