Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms

Abstract

In this paper we introduce a principled approach to modeling the image brightness constraint for optical flow algorithms. Using a simple noise model, we derive a probabilistic representation for optical flow. This representation subsumes existing approaches to flow modeling, provides insights into the behaviour and limitations of existing methods and leads to modified algorithms that outperform other approaches that use the brightness constraint. Based on this representation we develop algorithms for flow estimation using different smoothness assumptions, namely constant and affine flow. Experiments on standard data sets demonstrate the superiority of our approach.

Cite

Text

Govindu. "Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms." European Conference on Computer Vision, 2006. doi:10.1007/11744078_14

Markdown

[Govindu. "Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms." European Conference on Computer Vision, 2006.](https://mlanthology.org/eccv/2006/govindu2006eccv-revisiting/) doi:10.1007/11744078_14

BibTeX

@inproceedings{govindu2006eccv-revisiting,
  title     = {{Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms}},
  author    = {Govindu, Venu Madhav},
  booktitle = {European Conference on Computer Vision},
  year      = {2006},
  pages     = {177-188},
  doi       = {10.1007/11744078_14},
  url       = {https://mlanthology.org/eccv/2006/govindu2006eccv-revisiting/}
}