Home

Awesome

<img src='RGBD/images/overview.png' align="right" width=450, height=230 >

Mix-and-match-networks

[paper]

Mix and match networks: encoder-decoder alignment for zero-pair image translation
Yaxing Wang, Joost van de Weijer, Luis Herranz
CVPR2018

Introduction

This project is to do Mix-and-match-networks(M&Mnet) on color and RGBD datasets. We give two folders(color and RGBD) where we share corresponding codes and detail information to train our M&Mnet.

Dataset

<p align="center"><img width="100%" height='60%'src="RGBD/images/drawing1.png" /></p> <p align="center"><img width="60%" height='60%'src="RGBD/images/comparation.png" /></p>

If this work or color dataset are useful for your research, please cite papers:

@article{wang2018mix,
  title={Mix and match networks: encoder-decoder alignment for zero-pair image translation},
    author={Wang, Yaxing and van de Weijer, Joost and Herranz, Luis},
      journal={arXiv preprint arXiv:1804.02199},
        year={2018}
        }
 @article{yu2018weakly,
   title={Weakly Supervised Domain-Specific Color Naming Based on Attention},
     author={Yu, Lu and Cheng, Yongmei and van de Weijer, Joost},
       journal={arXiv preprint arXiv:1805.04385},
         year={2018}
         }

Contact

If you run into any problems with this code, please submit a bug report on the Github site of the project. For another inquries pleace contact with me: yaxing@cvc.uab.es