# DeepHarmonization

**Repository Path**: minskyli/DeepHarmonization

## Basic Information

- **Project Name**: DeepHarmonization
- **Description**: autoPS
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2018-12-04
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Deep Image Harmonization

![Alt Text](https://github.com/wasidennis/DeepHarmonization/blob/master/before_after.gif) 

Project webpage: https://sites.google.com/site/yihsuantsai/research/cvpr17-harmonization <br />
Contact: Yi-Hsuan Tsai (wasidennis at gmail dot com)

## Paper
[Deep Image Harmonization](https://arxiv.org/abs/1703.00069) <br />
Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu and Ming-Hsuan Yang <br />
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 find it useful for your research.

## Installation and Usage

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

* pre-trained model in 'model' 

* 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](http://vllab.ucmerced.edu/ytsai/CVPR17/real_data.zip).