himgupta1996/style-transfer-3d

2D-to-3D style transfer using Neural Renderer

This is the code for 2D-to-3D style transfer in the paper Neural 3D Mesh Renderer (CVPR 2018) by Hiroharu Kato, Yoshitaka Ushiku, and Tatsuya Harada.

Related repositories:

• Neural Renderer
  • Single-image 3D mesh reconstruction
  • 2D-to-3D style transfer
  • 3D DeepDream

Installation

# install neural_renderer
git clone https://github.com/hiroharu-kato/neural_renderer.git
cd neural_renderer
python setup.py install --user
# or, sudo python setup.py install

Example

bash ./examples/run.sh

Citation

@inproceedings{kato2018renderer
    title={Neural 3D Mesh Renderer},
    author={Kato, Hiroharu and Ushiku, Yoshitaka and Harada, Tatsuya},
    booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2018}
}

style-transfer-3d's Issues

What does values() mean?

Hi!

I don't know much about values(), and I'm not sure what it means.
What does values() mean?

features = self.vgg16(images, layers=['conv1_2', 'conv2_2', 'conv3_3', 'conv4_3']).values()
↑at Style-Transfer-3D/style_transfer_3d/main.py/extract_style_feature()

I think I can get the tensor without values, is that correct?

thank you

How can I run the program?

Hi, I thanks for your reimplementation with pytorch.

Could you please tell me how to run this code?

Thank you :)