ML Anthology

Spatial Reflectance Recovery Under Complex Illumination from Sparse Images

Li Shen, Haruo Takemura
CVPR 2006 pp. 1833-1838
doi:10.1109/CVPR.2006.287 /cvpr/2006/shen2006cvpr-spatial/

Abstract

A major challenge in inverse reflectometry is the acquisition of spatially varying materials. In this paper, we introduce a method to recover spatial reflectance from a sparse set of images under general illumination. Specifically, we first remove the high-frequency varying diffuse reflection term by using a low-order spherical harmonic approximation. This allows us to directly estimate the specular properties with a cluster fitting process, which simplifies the fitting processes and addresses the problem of data inadequacy for sparse images. As a result, we can reconstruct a truly spatially varying BRDF model of the surface from less than 10 images. Experimental results will be presented in order to demonstrate the effectiveness of the proposed algorithm.

CVPR Semantic Scholar

Cite

Text

Shen and Takemura. "Spatial Reflectance Recovery Under Complex Illumination from Sparse Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.287

Markdown

[Shen and Takemura. "Spatial Reflectance Recovery Under Complex Illumination from Sparse Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/shen2006cvpr-spatial/) doi:10.1109/CVPR.2006.287

BibTeX

@inproceedings{shen2006cvpr-spatial,
  title     = {{Spatial Reflectance Recovery Under Complex Illumination from Sparse Images}},
  author    = {Shen, Li and Takemura, Haruo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {1833-1838},
  doi       = {10.1109/CVPR.2006.287},
  url       = {https://mlanthology.org/cvpr/2006/shen2006cvpr-spatial/}
}