Skip to content

MathieuC3502/Edge-Preserving-Smoothing-and-Multi-Scale-Manipulation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

44 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Weighted Least Squares (WLS) Filter for Edge Preserving Smoothing and Multi Scale Manipulation

School Project Status Grade

The objective of this project is to implement the WLS Filter introduced by Z. Farbman, R. Fattal, D. Lischinski, and R. Szeliski in "Edge-preserving decompositions for multi-scale tone and detail manipulation", ACM Transactions on Graphics (TOG), 2008. Our goal is not to replicate the exact filter developed by the authors, but rather to leverage their findings to create our own implementation.

📃 The paper is available at http://szeliski.org/papers/Farbman-SG08.pdf (personnal website of one of the authors)

📁 Installation

To ensure the functionality of the scripts, the folders data and src must be placed at the root of the same folder. Downloading and extracting the .zip folder should result in a functionnal setup.

📋 Requirements

Required Libraries Library Documentation
Matplotlib https://matplotlib.org/
Numpy https://numpy.org/
Scipy.Sparse https://docs.scipy.org/doc/scipy/reference/sparse.html
PIL https://pillow.readthedocs.io/
Time https://docs.python.org/3/library/time.html

About

The objective of this project is to implement and present the results that were obtained by Z. Farbman, R. Fattal, D. Lischinski, and R. Szeliski in "Edge-preserving decompositions for multi-scale tone and detail manipulation, ACM Transactions on Graphics (TOG), 2008"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages