Clothes Parsing

This code is the implementation of the “A High Performance CRF Model for Clothes Parsing” paper. It contains all the code for being able to learn and run inference. The features for the Fashionista dataset must be downloaded separately.

Clothes Parsing
  • Type: library
  • Version: Dec, 2014
  • Language: matlab
  • License: CC-by-sa-nc 4.0
  • Dependencies


This code provides an implementation of the research paper:

A High Performance CRF Model for Clothes Parsing
Edgar Simo-Serra, Sanja Fidler, Francesc Moreno-Noguer, and Raquel Urtasun
Asian Conference on Computer Vision (ACCV), 2014

The code here allows training and testing of a model that got state-of-the-art results on the Fashionista dataset at the time of publication.


Copyright (C) <2014> <Edgar Simo-Serra, Sanja Fidler, Francesc Moreno-Noguer, Raquel Urtasun>

This work is licensed under the Creative Commons
Attribution-NonCommercial-ShareAlike 4.0 International License. To view a copy
of this license, visit or
send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.

Edgar Simo-Serra, Institut de Robotica i Informatica Industrial (CSIC/UPC), December 2014.,
Copyright (C) <2014> <Edgar Simo-Serra>


In order to get started first checkout out the source code and then extract the features:

# Check out the git and cd into it as working directory
git clone
cd clothes_parsing
# Get and unpack the necessary features
tar xvjf poseseg.tar.bz2

The dSP dependency must also be compiled. This can be done by:

cd lib/dSP_5.1
make # First edit the Makefile if necessary


You can reproduce results simply by running from Matlab:

sm = segmodel( 'PROFILE', '0.16', 'use_real_pose', false ); % Load the model, parameters can be set here
sm = sm.train_misc_unaries(); % Trains some misc stuff
sm = sm.train_MRF(); % Actually sets up and trains the CRF
R = sm.test_MRF_segmentation() % Performs testing and outputs results

This should generate an output like:

    logreg:       29
    cpmc_logreg:  29
 Initializing Image 011 / 350...   0.4 seconds!   


 Tested MRF in 319.0 seconds
 350 / 350... 

 R = 

     confusion: [29x29 double]
     order: [29x1 double]
     acc: 0.8432
     pre: [29x1 double]
     rec: [29x1 double]
     f1: [29x1 double]
     voc: [29x1 double]
     avr_pre: 0.3007
     avr_rec: 0.3292
     avr_f1: 0.3039
     avr_voc: 0.2013

Please note that due to stochastic components and differences between software versions, the numbers will not be exactly the same as the paper. For the paper all results were obtained on a linux machine running Ubuntu 12.04 with Matlab R2012a ( 64-bit (glnxa64).

You can furthermore visualize the output of the model with:

sm.test_MRF_visualize( 'output/' )

This will save both the ground truth segmentations and the predicted segmentations in the directory ‘output/’ as shown in the paper.

If you use this code please cite:

   author = {Edgar Simo-Serra and Sanja Fidler and Francesc Moreno-Noguer and Raquel Urtasun},
   title = {{A High Performance CRF Model for Clothes Parsing}},
   booktitle = "Proceedings of the Asian Conference on Computer Vision (2014)",
   year = 2014


We would like to give our thanks to Kota Yamaguchi for his excellent code which we have used as a base for our model.

The different codes we have used (in alphabetical order):


December 2014: Initial version 1.0 release