Autoencoder for Diverse 3D Shape Collections

Some simple Blender scripts for rendering paper figures

Python implementation of "MAPS: Multiresolution Adaptive Parameterization of Surfaces"

The open source mesh processing python library

Transfer Learning using Spectral Convolutional Autoencoders on Semi-Regular Surface Meshes; accepted at Learning on Graphs Conference 2022

Python implementation of Functional Maps

Pytorch implementation of DiffusionNet for fast and robust learning on 3D surfaces like meshes or point clouds.

🍪 A cookiecutter package for an enlightened python package

J. Solomon, F. de Goes, G. Peyré, M. Cuturi, A. Butscher, A. Nguyen, T. Du, L. Guibas. Convolutional Wasserstein Distances: Efficient Optimal Transportation on Geometric Domains. ACM Transactions o…

Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than tradi…

Subdivision-based Mesh Convolutional Networks.

Code for the SIGGRAPH 2017 paper "Convolutional Neural Networks on Surfaces via Seamless Toric Covers"

libigl python bindings

Official implementation of Dynamical VAEs

prototype code for neural subdivision

CoSMA: Convolutional Semi-Regular Mesh Autoencoder. Accepted at WACV 2022

Website for the Seminar on Learning Theory, taught WS18/19 by Michael Kamp and Pascal Welke

Reconstruct Watertight Meshes from Point Clouds [SIGGRAPH 2020]