ML Anthology

Recovering Photometric Properties of Multiple Strongly-Reflective, Partially-Transparent Surfaces from a Single Image

José P. Queiroz-Neto, Rodrigo L. Carceroni, Lara C. R. Coelho
ICCV 2005 pp. 1409-1416
doi:10.1109/ICCV.2005.205 /iccv/2005/queirozneto2005iccv-recovering/

Abstract

This paper introduces a method to recover photometric parameters of a set of 3D surfaces from a single image with significant global-illumination effects such as inter-reflections and transparencies. Since this problem is ambiguous for arbitrary unknown scenes, our formulation assumes that the scene consists of a small set of photometrically homogeneous surfaces with known 3D shapes, illuminated by known light sources. We show that under these conditions, the system of nonlinear equations that defines how the image is formed may be factorized into a vector composed only of products of some photometric parameters, and a matrix, whose elements depend non-linearly on both the known illumination, the known 3D shapes and the remaining photometric parameters. This factorization leads to an efficient optimization-based algorithm to compute all unknown photometric parameters from a single input image. Experiments with real data show that this algorithm is more stable and efficient than simpler alternatives

ICCV Semantic Scholar

Cite

Text

Queiroz-Neto et al. "Recovering Photometric Properties of Multiple Strongly-Reflective, Partially-Transparent Surfaces from a Single Image." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.205

Markdown

[Queiroz-Neto et al. "Recovering Photometric Properties of Multiple Strongly-Reflective, Partially-Transparent Surfaces from a Single Image." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/queirozneto2005iccv-recovering/) doi:10.1109/ICCV.2005.205

BibTeX

@inproceedings{queirozneto2005iccv-recovering,
  title     = {{Recovering Photometric Properties of Multiple Strongly-Reflective, Partially-Transparent Surfaces from a Single Image}},
  author    = {Queiroz-Neto, José P. and Carceroni, Rodrigo L. and Coelho, Lara C. R.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1409-1416},
  doi       = {10.1109/ICCV.2005.205},
  url       = {https://mlanthology.org/iccv/2005/queirozneto2005iccv-recovering/}
}