ML Anthology

Bayesian Nonparametric Intrinsic Image Decomposition

Jason Chang, Randi Cabezas, John W. Fisher Iii
ECCV 2014 pp. 704-719
doi:10.1007/978-3-319-10593-2_46 /eccv/2014/chang2014eccv-bayesian/

Abstract

We present a generative, probabilistic model that decomposes an image into reflectance and shading components. The proposed approach uses a Dirichlet process Gaussian mixture model where the mean parameters evolve jointly according to a Gaussian process. In contrast to prior methods, we eliminate the Retinex term and adopt more general smoothness assumptions for the shading image. Markov chain Monte Carlo sampling techniques are used for inference, yielding state-of-the-art results on the MIT Intrinsic Image Dataset.

PDF ECCV Semantic Scholar

Cite

Text

Chang et al. "Bayesian Nonparametric Intrinsic Image Decomposition." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10593-2_46

Markdown

[Chang et al. "Bayesian Nonparametric Intrinsic Image Decomposition." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/chang2014eccv-bayesian/) doi:10.1007/978-3-319-10593-2_46

BibTeX

@inproceedings{chang2014eccv-bayesian,
  title     = {{Bayesian Nonparametric Intrinsic Image Decomposition}},
  author    = {Chang, Jason and Cabezas, Randi and Iii, John W. Fisher},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {704-719},
  doi       = {10.1007/978-3-319-10593-2_46},
  url       = {https://mlanthology.org/eccv/2014/chang2014eccv-bayesian/}
}