Generating Fantasy Planets with Generative Adversarial Networks

by , | Jun 12, 2023 | Neuroinformatics, Paper

Decorative post picture
Do you want to know how planets millions of light years away from us might look like?

Step outside our solar system with GANiverse. This paper presents a Generative Adversarial Network (GAN) that generates fantasy planets resembling celestial bodies in our solar system based on a dataset comprising the color, texture, and structure of planets and moons closer to Earth.

Spoiler Alert:
GANiverse successfully generates fantasy celestial objects with realistic textures, sources of light, and rich coloring by employing a loss function comprising of the Wasserstein-GAN loss and the Structural Similarity Index (SSIM). You can access the author’s work (finalized in July 2022) directly and create your own fake planet on their website.

Good to know:
To better understand our research, it is helpful to have knowledge of Generative Adversarial Networks (GANs), their architecture and applications. Alternatively, some understanding of Deep Learning and Neural Networks may be enough to guide you through our main findings.

Course:

Computer Vision, Applied research paper for ‘Projects in Deep Computer Vision’ taught by Axel Schaffland. ST 22

Loader Loading...
EAD Logo Taking too long?

Reload Reload document
| Open Open in new tab
Christian Burmester

Christian Burmester

“As someone who is passionate about astronomy and the exploration of our galaxy, utlising GANs in this context was an exciting experience for me. It was thrilling to interpolate from existing data of our solar system and discover new possibilities. The beauty and diversity of planets our GAN generated amazed me. It’s incredible and mind boggling to think about the endlessness of unique combinations of pixels that are out there that we as humans can make sense of (or not).”
Maximilian Kalcher

Maximilian Kalcher

“This project combines my passion for generative neural networks with my fascination for the universe. Since we can’t see many planets outside of our solar system, we designed a generative model that creates unique, realistic planets based on what we know about the universe. Through this project, we hope to explore the potential of artificial intelligence to help us better understand and appreciate the beauty of our universe.”

You could also be interested in…