Skip to content

This is a neural network approximating the two-dimensional signed distance functions of polygons.

License

Notifications You must be signed in to change notification settings

mintpancake/2d-sdf-net

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

2d-sdf-net

This is a neural network approximating the two-dimensional signed distance functions of polygons. The network structure references DeepSDF: https://github.com/facebookresearch/DeepSDF.

Intro

  • The signed distance function determines the minimum distance of a point to the boundary of a curve.
  • The function is negative inside and positive outside.
  • The zero-contour is the boundary of the curve.
Sampled curve
Before truncation
After truncation

Requirements

  • PyTorch
  • Tensorboard
  • OpenCV

Get Started

  1. code/drawer.py
  2. code/sampler.py
  3. code/trainer.py
  4. code/renderer.py

About

This is a neural network approximating the two-dimensional signed distance functions of polygons.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages