/CreaturesResult

Scripts for viewing Creatures Great and SMAL results.

Primary LanguagePython

Creatures Great and SMAL - Result Viewer

Scripts for viewing Creatures Great and SMAL results.

Installation

  1. Clone the repository with submodules and enter directory

    git clone --recurse-submodules https://github.com/benjiebob/CreaturesResult
    cd CreaturesResult
     
    
  2. Install the Neural Mesh Renderer submodule (which originated from my fork), which includes a render_points function

    pip install -e neural_renderer
    
    
  3. Download texture map (from smal/dog_texture.pkl) and a version of SMAL 2017 converted to NumPy (smal_CVPR2017_np.pkl) from my Google Drive and place under the smal folder

  4. Download the preliminary Maggie result data

  5. Install dependencies, particularly PyTorch (with cuda support)

  6. Edit the IMAGE_DIR and RESULT_DIR paths in result_viewer.py to reflect your own file structure

  7. Test the python3 script

    python result_viewer.py
    

Acknowledgements

This work was completed in relation to the following paper:

@inproceedings{biggs2018creatures,
  title={{C}reatures great and {SMAL}: {R}ecovering the shape and motion of animals from video},
  author={Biggs, Benjamin and Roddick, Thomas and Fitzgibbon, Andrew and Cipolla, Roberto},
  booktitle={ACCV},
  year={2018}
}