ML Anthology

Pose-Robust Albedo Estimation from a Single Image

Soma Biswas, Rama Chellappa
CVPR 2010 pp. 2683-2690
doi:10.1109/CVPR.2010.5539987 /cvpr/2010/biswas2010cvpr-pose/

Abstract

We present a stochastic filtering approach to perform albedo estimation from a single non-frontal face image. Albedo estimation has far reaching applications in various computer vision tasks like illumination-insensitive matching, shape recovery, etc. We extend the formulation proposed in that assumes face in known pose and present an algorithm that can perform albedo estimation from a single image even when pose information is inaccurate. 3D pose of the input face image is obtained as a byproduct of the algorithm. The proposed approach utilizes class-specific statistics of faces to iteratively improve albedo and pose estimates. Illustrations and experimental results are provided to show the effectiveness of the approach. We highlight the usefulness of the method for the task of matching faces across variations in pose and illumination. The facial pose estimates obtained are also compared against ground truth.

CVPR Semantic Scholar

Cite

Text

Biswas and Chellappa. "Pose-Robust Albedo Estimation from a Single Image." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539987

Markdown

[Biswas and Chellappa. "Pose-Robust Albedo Estimation from a Single Image." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/biswas2010cvpr-pose/) doi:10.1109/CVPR.2010.5539987

BibTeX

@inproceedings{biswas2010cvpr-pose,
  title     = {{Pose-Robust Albedo Estimation from a Single Image}},
  author    = {Biswas, Soma and Chellappa, Rama},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {2683-2690},
  doi       = {10.1109/CVPR.2010.5539987},
  url       = {https://mlanthology.org/cvpr/2010/biswas2010cvpr-pose/}
}