“Terra Mars: When Earth Shines on Mars Through AI’s Imagination” by Weili

  • ©Shi Weili

  • ©Shi Weili

Conference:


Type:


Title:

    Terra Mars: When Earth Shines on Mars Through AI's Imagination

Presenter(s)/Author(s):



Abstract:


    Terra Mars presents Mars in the visual style of Earth. An ANN was trained to learn the relation between topographical data and satellite imagery of Earth and was applied to topographical data of Mars to generate imaginary satellite images. This project suggests a new approach to creative applications of AI.

    Terra Mars presents artistic renderings of Mars with visual reference to our very own planet Earth. The author trained an artificial neural network with topographical data and satellite imagery of Earth so that it can learn the relation between them. The author then applied the trained model to topographical data of Mars to generate images that resemble satellite imagery of Earth. This project suggests a new approach to creative applications of artificial intelligence—using its capability of remapping to broaden the domain of artistic imagination.

References:


    1. Apollo 17 crew, Apollo Image Library (NASA, 1972) AS17-148-22727.
    2. F. White, The Overview Effect: Space Exploration and Human Evolution (New York: Houghton-Mifflin, 1987).
    3. B. Grant, T. Dougherty and E. Anderson, Daily Overview, www.dailyoverview.com (2013), accessed 15 January 2019.
    4. F.B. Salisbury, “Martian Biology,” Science 136, No. 3510, 17–26 (1962)
    5. “Blue Marble: Next Generation” (NASA, 2005).
    6. “Blue Marble” (NASA, 2002).
    7. Mars HRSC MOLA Blended DEM Global 200m v2 (U.S. Geological Survey, 2017).
    8. P. Isola et al., “Image-to-Image Translation with Conditional Adversarial Networks,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition 2017, 5967–5976.
    9. T.C. Wang et al., “High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2018, 8798–8807.
    10. N. Jetchev, U. Bergmann and R. Vollgraf, “Texture Synthesis with Spatial Generative Adversarial Networks,” arXiv preprint, arXiv:1611.08207 (2016).
    11. S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” Proceedings of the International Conference on Machine Learning 2015, 448–456.
    12. D. Ulyanov, A. Vedaldi and V. Lempitsky, “Instance Normalization: The Missing Ingredient for Fast Stylization,” arXiv preprint, arXiv:1607.08022 (2016).
    13. P. Micikevicius et al. “Mixed Precision Training,” International Conference on Learning Representations 2018.
    14. T. Chen et al. “Training Deep Nets with Sublinear Memory Cost,” arXiv preprint, arXiv:1604.06174 (2016).
    15. K. Gill, Living Mars, www.flickr.com/photos/kevinmgill/sets/72157651708639278 (Flickr, 2012–2018), accessed 15 January 2019.
    16. Ittiz, Realistic Mars, www.deviantart.com/ittiz/art/Realistic-Mars-146486184 (DeviantArt, 2009), accessed 15 January 2019.


Additional Images:

©Shi Weili ©Shi Weili ©Shi Weili ©Shi Weili ©Shi Weili ©Shi Weili

ACM Digital Library Publication:



Overview Page:


Art Paper/Presentation Type: