Official implementation for the paper "SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization".

SAPE

Project page     Paper

Official implementation for the paper "SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization".

Environment

Create an anaconda environment and install Pytorch. Install other dependencies:

conda env update --file environment.yml

Tasks

Running examples:

python tasks_func_1d.py
python tasks_image_2d.py 
   
    
python tasks_silhouette_2d.py 
    
     
python tasks_occupancy_3d.py 
     

     
    
   

See ./assets directory for possible input files.

Models and other outputs (images, optimization animation, etc.) will be saved under ./assets/checkpoints/ /

Citation

If you find this code useful for your research, please cite our paper.

@inproceedings{hertz2021sape,
  title={SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization},
  author={Hertz, Amir and Perel, Or and Giryes, Raja and Sorkine-Hornung, Olga and Cohen-Or, Daniel},
  booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},
  year={2021}
}