Skip to content

Official implementation of MagicClay: Sculpting Meshes with Generative Neural Fields (Siggraph Asia 2024)

License

Notifications You must be signed in to change notification settings

amirbarda/MagicClay

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MagicClay: Sculpting Meshes with Generative Neural Fields

Project Page | Paper |

This is the official implementation of MagicClay. For ease of use, it is implemeneted as a Threestudio extension.

alt text

IMAGE ALT TEXT HERE IMAGE ALT TEXT HERE IMAGE ALT TEXT HERE

How to Install and Run

  1. follow the installation instruction for Threestudio
  2. install the following:
    pip install torch-scatter
    pip install cyobj
    pip install ConfigArgParse
  3. put the threestudio-magicclay folder inside the 'custom' folder in the main Threestudio installation.
  4. download demo data here
  5. put the demo data in a folder called demo_data in the threestudio-magicclay folder, to run the relevant demos in magicclay_demo.sh

If you found this work helpful, please cite as:

@article{Barda24,
title = {MagicClay: Sculpting Meshes With Generative Neural Fields},
author = {Amir Barda and Vladimir G. Kim and Noam Aigerman and Amit H. Bermano and Thibault Groueix},
year = {2024},
journal = {SIGGRAPH Asia (Conference track)}}

About

Official implementation of MagicClay: Sculpting Meshes with Generative Neural Fields (Siggraph Asia 2024)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published