Deep Photo Style Transfer - 通过深度学习改变图片风格

阅读 193
收藏 1
2017-04-24
原文链接:github.com

Code and data for paper "Deep Photo Style Transfer"

Disclaimer

This software is published for academic and non-commercial use only.

Setup

This code is based on torch. It has been tested on Ubuntu 14.04 LTS.

Dependencies:

CUDA backend:

Download VGG-19:

sh models/download_models.sh

Compile cuda_utils.cu (Adjust PREFIX and NVCC_PREFIX in makefile for your machine):

make clean && make

Usage

Quick start

To generate all results (in examples/) using the provided scripts, simply run

run('gen_laplacian/gen_laplacian.m')

in Matlab or Octave and then

python gen_all.py

in Python. The final output will be in examples/final_results/.

Basic usage

  1. Given input and style images with semantic segmentation masks, put them in examples/ respectively. They will have the following filename form: examples/input/in<id>.png, examples/style/tar<id>.png and examples/segmentation/in<id>.png, examples/segmentation/tar<id>.png;
  2. Compute the matting Laplacian matrix using gen_laplacian/gen_laplacian.m in Matlab. The output matrix will have the following filename form: gen_laplacian/Input_Laplacian_3x3_1e-7_CSR<id>.mat;
  3. Run the following script to generate segmented intermediate result:
th neuralstyle_seg.lua -content_image <input> -style_image <style> -content_seg <inputMask> -style_seg <styleMask> -index <id> -serial <intermediate_folder>
  1. Run the following script to generate final result:
th deepmatting_seg.lua -content_image <input> -style_image <style> -content_seg <inputMask> -style_seg <styleMask> -index <id> -init_image <intermediate_folder/out<id>_t_1000.png> -serial <final_folder> -f_radius 15 -f_edge 0.01

You can pass -backend cudnn and -cudnn_autotune to both Lua scripts (step 3. and 4.) to potentially improve speed and memory usage. libcudnn.so must be in your LD_LIBRARY_PATH. This requires cudnn.torch.

Image segmentation

Note: In the main paper we generate all comparison results using automatic scene segmentation algorithm modified from DilatedNet. Manual segmentation enables more diverse tasks hence we provide the masks in examples/segmentation/.

The mask colors we used (you could add more colors in ExtractMask function in two *.lua files):

Color variable RGB Value Hex Value
blue 0 0 255 0000ff
green 0 255 0 00ff00
black 0 0 0 000000
white 255 255 255 ffffff
red 255 0 0 ff0000
yellow 255 255 0 ffff00
grey 128 128 128 808080
lightblue 0 255 255 00ffff
purple 255 0 255 ff00ff

Here are some automatic and manual tools for creating a segmentation mask for a photo image:

Automatic:

Manual:

Examples

Here are some results from our algorithm (from left to right are input, style and our output):

Acknowledgement

  • Our torch implementation is based on Justin Johnson's code;
  • We use Anat Levin's Matlab code to compute the matting Laplacian matrix.

Citation

If you find this work useful for your research, please cite:

@article{luan2017deep,
  title={Deep Photo Style Transfer},
  author={Luan, Fujun and Paris, Sylvain and Shechtman, Eli and Bala, Kavita},
  journal={arXiv preprint arXiv:1703.07511},
  year={2017}
}

Contact

Feel free to contact me if there is any question (Fujun Luan fl356@cornell.edu).

评论