Learning to Tile with Self-Supervised Graph Neural Network
TilinGNN
TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network (SIGGRAPH 2020)
About
The goal of our research problem is illustrated below: given a tile set (a) and a 2D region to be filled (b), we aim to produce a tiling (c) that maximally covers the interior of the given region without overlap or hole between the tile instances.
Dependencies:
This project is implemented in Python 3.7. You need to install the following packages to run our program.
- Pytorch (tested with v1.2.0): compulsory, to manipulate the tensors on GUP, and to build up the networks.
- Pytorch Geometric (tested with v1.3.2): compulsory, to build up the graph networks.
- Numpy: compulsory, to manipulate the arrays and their computations.
- Shapely (tested