Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application

Bumsoo Kim1, 2, Sanghyun Byun3, Yonghoon Jung3,
Wonseop Shin3, Sareer UI Amin4, Sanghun Seo*
1,*School of Art and Technology, Chung-Ang University, Korea
2VIVE STUDIOS
3GSAIM, Chung-Ang University, Korea
4Department of Computer Science and Engineering, Chung-Ang University, Korea
(Accepted as Spotlight) NeurIPS 2023 Workshop on ML4CD (Machine Learning for Creativity and Design)
*Indicates Corresponding Author
Paper Code

For Minecraft-World texture generation, we proposed user-friendly AI-tool which can generate frontal face texture and edit it by text-guidance.

Abstract

In this paper, we first present the character texture generation system Minecraft-ify, specified to Minecraft video game toward in-game application. Ours can generate face-focused image for texture mapping tailored to 3D virtual character having cube manifold. While existing projects or works only generate texture, proposed system can inverse the user-provided real image, or generate average/random appearance from learned distribution. Moreover, it can be manipulated with text-guidance using StyleGAN and StyleCLIP. These features provide a more extended user experience with enlarged freedom as a user-friendly AI-tool. Project page can be found at https: //gh-bumsookim.github.io/Minecraft-ify/

BibTeX

@article{Minecraft-ify2023,
        title = {Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application},
        author = {Bumsoo Kim, Sanghyun Byun, Yonghoon Jung, Wonseop Shin, Sareer UI Amin, Sanghyun Seo},
        journal={arXiv preprint arxiv:2309.XXXXX},
        year={2023}
        }