This repo provides the code implementation of the paper Efficient High-Resolution Image-to-Image Translation using Multi-Scale Gradient U-Net. More specificallly to train on a specific dataset, include that dataset in the datasets folder.
- python 3.6
- Tensorflow 1.12
- Keras
- Cuda toolkit 9.0
- Cudnn
- Download any of the datasets mentioned in the paper Link to Paper
- Make sure you have all the requirements installed, then after run train.ipynb
- To replicate the results in the paper, run test.ipynb by making appropriate changes by using weights produced by train.ipynb
- Uplift the poses from 2d to 3d from the below link 3D Pose estimation Baseline
- Place output of the step 4 in unity assets folder and run it to watch the animation