Non-Parametric Filtering for Geometric Detail Extraction and Material Representation

Zicheng Liao, Jason Rock, Yang Wang, David Forsyth

CVPR 2013

doi:10.1109/CVPR.2013.129 /cvpr/2013/liao2013cvpr-nonparametric/

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.

PDF CVPR Semantic Scholar

Cite

Text

Liao et al. "Non-Parametric Filtering for Geometric Detail Extraction and Material Representation." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.129

Markdown

[Liao et al. "Non-Parametric Filtering for Geometric Detail Extraction and Material Representation." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/liao2013cvpr-nonparametric/) doi:10.1109/CVPR.2013.129

BibTeX

@inproceedings{liao2013cvpr-nonparametric,
  title     = {{Non-Parametric Filtering for Geometric Detail Extraction and Material Representation}},
  author    = {Liao, Zicheng and Rock, Jason and Wang, Yang and Forsyth, David},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.129},
  url       = {https://mlanthology.org/cvpr/2013/liao2013cvpr-nonparametric/}
}