Skip to content

92xianshen/PyDCRF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PyDCRF

This is a Python-based Dense CRF implementation for Philipp Krähenbühl's Fully-Connected CRFs.

This code is inspired by PyDenseCRF (https://github.com/lucasb-eyer/pydensecrf) and CRFasRNN-keras (https://github.com/sadeepj/crfasrnn_keras).

The mean-field approximation is implemeneted in Python, but the high-dim filtering for efficient message passing is implemented in C using Cython-based wrapper.

Please cite

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
Philipp Krähenbühl and Vladlen Koltun
NIPS 2011

and this repo if the code is of help for your research.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published