This is the official implementation of [Flatten Anything Model (FAM)], an unsupervised neural architecture to achieve global free-boundary surface parameterization via learning point-wise mappings between 3D points on the target geometric surface and adaptively-deformed UV coordinates within the 2D parameter domain. This code has been tested with Python 3.9, PyTorch 1.10.1, CUDA 11.1 and cuDNN 8.0.5 on Ubuntu 20.04.
-
Within
cdbs/CD/
, runpython setup.py install
for compilation. -
Within
cdbs/EMD/
, runpython setup.py install
andcp build/lib.linux-x86_64-cpython-39/emd_cuda.cpython-39-x86_64-linux-gnu.so .
for compilation. -
A demo script for running FAM is provided in a jupyter notebook
scripts/main.ipynb
.