All Projects → awjuliani → Pix2pix Film

awjuliani / Pix2pix Film

Licence: mit
An implementation of Pix2Pix in Tensorflow for use with frames from films

Projects that are alternatives of or similar to Pix2pix Film

Starnet
StarNet
Stars: ✭ 141 (-12.96%)
Mutual labels:  jupyter-notebook, gan, pix2pix
Swapnet
Virtual Clothing Try-on with Deep Learning. PyTorch reproduction of SwapNet by Raj et al. 2018. Now with Docker support!
Stars: ✭ 202 (+24.69%)
Mutual labels:  jupyter-notebook, gan, pix2pix
Tensorflow2.0 Examples
🙄 Difficult algorithm, Simple code.
Stars: ✭ 1,397 (+762.35%)
Mutual labels:  jupyter-notebook, gan, pix2pix
Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (-12.96%)
Mutual labels:  gan, pix2pix
Cyclegan
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Stars: ✭ 10,933 (+6648.77%)
Mutual labels:  gan, pix2pix
Deep Learning With Python
Example projects I completed to understand Deep Learning techniques with Tensorflow. Please note that I do no longer maintain this repository.
Stars: ✭ 134 (-17.28%)
Mutual labels:  jupyter-notebook, gan
Psgan
Periodic Spatial Generative Adversarial Networks
Stars: ✭ 108 (-33.33%)
Mutual labels:  jupyter-notebook, gan
Unit
Unsupervised Image-to-Image Translation
Stars: ✭ 1,809 (+1016.67%)
Mutual labels:  gan, pix2pix
Data science blogs
A repository to keep track of all the code that I end up writing for my blog posts.
Stars: ✭ 139 (-14.2%)
Mutual labels:  jupyter-notebook, gan
Tensorflow Pix2pix
A lightweight pix2pix Tensorflow implementation.
Stars: ✭ 143 (-11.73%)
Mutual labels:  gan, pix2pix
Pix2pixbegan.pytorch
A pytorch implementation of pix2pix + BEGAN (Boundary Equilibrium Generative Adversarial Networks)
Stars: ✭ 148 (-8.64%)
Mutual labels:  gan, pix2pix
Capsule Gan
Code for my Master thesis on "Capsule Architecture as a Discriminator in Generative Adversarial Networks".
Stars: ✭ 120 (-25.93%)
Mutual labels:  jupyter-notebook, gan
Sketch To Art
🖼 Create artwork from your casual sketch with GAN and style transfer
Stars: ✭ 115 (-29.01%)
Mutual labels:  gan, pix2pix
Generative adversarial networks 101
Keras implementations of Generative Adversarial Networks. GANs, DCGAN, CGAN, CCGAN, WGAN and LSGAN models with MNIST and CIFAR-10 datasets.
Stars: ✭ 138 (-14.81%)
Mutual labels:  jupyter-notebook, gan
Deepnudecli
DeepNude Command Line Version With Watermark Removed
Stars: ✭ 112 (-30.86%)
Mutual labels:  gan, pix2pix
P2pala
Page to PAGE Layout Analysis Tool
Stars: ✭ 147 (-9.26%)
Mutual labels:  gan, pix2pix
Pytorch Gan
A minimal implementaion (less than 150 lines of code with visualization) of DCGAN/WGAN in PyTorch with jupyter notebooks
Stars: ✭ 150 (-7.41%)
Mutual labels:  jupyter-notebook, gan
Deblurgan
Image Deblurring using Generative Adversarial Networks
Stars: ✭ 2,033 (+1154.94%)
Mutual labels:  gan, pix2pix
Stylegan2 Projecting Images
Projecting images to latent space with StyleGAN2.
Stars: ✭ 102 (-37.04%)
Mutual labels:  jupyter-notebook, gan
Ganotebooks
wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch
Stars: ✭ 1,446 (+792.59%)
Mutual labels:  jupyter-notebook, pix2pix

Pix2Pix-Film

alt text

An implementation of Pix2Pix in Tensorflow for use with colorizing and increasing the field of view in frames from classic films. For more information, see my Medium Post on the project.

Pretrained model available here. It was trained using Alfred Hitchcock films, so it generalizes best to similar movies.

To generate frames, use ffmpeg to resize and create .png frames from video.

  • To resize video: ffmpeg -strict -2 -i input.mp4 -vf scale=256:144 output.mp4 -strict -2

  • To generate frames: ffmpeg -i output.mp4 -vf fps=10 ./frames/out%6d.png

In order to 'remaster' frames, run Pix2Pix iPython notebook.

To convert 'remastered' frames back into a video, use: ffmpeg -framerate 10 -i frame%01d.png -c:v libx264 -r 30 -pix_fmt yuv420p out.mp4

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].