Deep Image Harmonization 文章相关代码信息

emo code of the paper: "Deep Image Harmonization", Y.-H. Tsai, X. Shen, Z. Lin, K. Sunkavalli, X. Lu and M.-H. Yang, CVPR 2017

•  28 commits
•  1 branch
•  0 releases
•  1 contributor

1.  Python 100.0%

Python

Clone or download 

Find file

Branch: master 

New pull request

Latest commit bde199b on 17 May  wasidennis committed on GitHub  Update README.md

	data	release DeepHarmonization v1	5 months ago
	model	release DeepHarmonization v1	5 months ago
	README.md	Update README.md	3 months ago
	demo.py	release DeepHarmonization v1	5 months ago

 README.md

Deep Image Harmonization

Project webpage: https://sites.google.com/site/yihsuantsai/research/cvpr17-harmonization 
Contact: Yi-Hsuan Tsai (ytsai2 at ucmerced dot edu)

Paper

Deep Image Harmonization 
Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu and Ming-Hsuan Yang 
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

This is the authors' demo code described in the above paper. Please cite our paper if you use it for your research.

Installation and Usage

• Download and unzip the code.

• Install Caffe: http://caffe.berkeleyvision.org/.

• Download the pre-trained caffe model and move it under the model folder.

• Run demo.py on real composite images (including our test set collected in the paper).

Evaluation Set

• Download our complete set of real composite images, including our harmonization results here.

Note

The model, code and dataset are available for non-commercial research purposes only.

Log

• 03/2017: demo code released
• 05/2017: complete evaluation set released