TilesetNet: An Amateur CNN Autoencoder
A Convolutional Neural Network that turns basic concept art, portraits or gameplay screenshots into usable tilesets! It still has a long way to go, but it was a fun and rewarding project!
Citations (seen on bottom right of frames that use them):
[1] Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "Image style transfer using convolutional neural networks." 2016 IEEE conference on computer vision and pattern recognition (CVPR), 2016.
[2] Fu, Qiwen, Wei-Ting Hsu, and Mu-Heng Yang. "Colorization using ConvNet and GAN." 2017. Available: Stanford, http://cs231n.stanford.edu/reports/2017/pdfs/302.pdf. [Accessed April 29, 2020].
[3] O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 234–241. Springer, 2015.
Other Videos By The Good Trash
2024-03-09 | Solve the Puzzle!!! Key Chasm |
2023-04-07 | FNAF Stalemate: The Deadly Precedent of Security Breach |
2022-08-07 | Luna Bay Trailer |
2022-02-26 | Testimony of a Christian Programmer |
2021-10-16 | Am2R is a Metroid: Am2R Matters |
2021-10-16 | Metroid Matters: The Best Franchise |
2021-10-15 | Back in Action: Metroid Fusion Matters |
2021-10-14 | PREVIEW - Metroid Matters |
2021-08-06 | STARBOUND: A Tale of Debt and Dismemberment |
2020-08-02 | SKELETON WARS Fake Trailer |
2020-05-01 | TilesetNet: An Amateur CNN Autoencoder |