Skip to content

pieris98/team13

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

team13

Team 13 repository for ML3D course project @KAIST

Introduction

This is our project "Geometric Deep Learning for 3D Shape Correspondence". It explores several recent methods on 3D Shape correspondence, including:

Code and Data

The README in each folder explains the prerequisite development environment, code and data needed.

Evaluation

Our code is evaluated on the FAUST Humans dataset[5], a standard realistic benchmark for 3D Shape Correspondence methods.

References

[1] Masci, J. et al. 2015. Geodesic Convolutional Neural Networks on Riemannian Manifolds. 2015 IEEE International Conference on Computer Vision Workshop (ICCVW) (Dec. 2015)

[2] Federico Monti, Davide Boscaini, Jonathan Masci, Emanuele Rodolà, Jan Svoboda, & Michael M. Bronstein. (2016). Geometric deep learning on graphs and manifolds using mixture model CNNs.

[3] Nicolas Donati, Abhishek Sharma, & Maks Ovsjanikov. (2020). Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence.

[4] Sharp, N. et al. 2022. DiffusionNet: Discretization Agnostic Learning on Surfaces. arXiv.

[5] Bogo, F. et al. 2014. FAUST: Dataset and Evaluation for 3D Mesh Registration. 2014 IEEE Conference on Computer Vision and Pattern Recognition (Columbus, OH, USA, Jun. 2014)

About

Team 13 for ML3D course @kaist

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published