Uncanny Rd. – Drawing tool to interactively synthesise street images

Uncanny Rd. is a drawing tool that allows users to interactively synthesise street images with the help of Generative Adversarial Networks (GANs). The project was created as a collaboration between Anastasis Germanidis and Cristobal Valenzuela to explore new kinds of human-machine collaboration that deep learning can enable.

The project and uses two AI research papers published last year as a starting point (Image-to-Image Translation Using Conditional Adversarial Networks by Isola et al. and High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs by Wang et al.)  Users are asked to interact with a semantic colormap of a scene, where each color represents a different kind of object label (e.g. road, building, vegetation, etc.). The neural network model was trained using adversarial learning on the Cityscapes dataset, which contains street images from a number of German cities.

Support CreativeApplications.Net

Since 2008, CreativeApplications.Net (CAN) has been a driving force, tirelessly influencing and shaping the conversations surrounding technology, society, and critical making. With a community of 1600+ members and a vast library boasting over 3,500 meticulously curated projects, experiments, texts, and reviews, CAN stands resolute as an unparalleled resource for students, educators, practitioners, curators, and cultural producers.

However, as we navigate the stark reality of independent publishing, we need your help! Please embark on this journey with us, extending your support by joining our community as a Member and contributing to our shared mission of propelling CAN forward.

Joining CAN is only $20 per year! (less than $2 per month) and it includes:

  • Access thousands of projects, scores of essays, interviews and reviews.
  • Post your projects, events, announcements.
  • Join our Discord for events, open calls and even more projects.
  • Tutorials (beginners and advanced) with code examples and downloads.
  • Find employers who have recruited here in the past (over 1,000 jobs).
  • Special offers and giveaways (events, books and media).
  • No advertisements or banners of any kind, ad-free reading!

Joining CAN as an organisation (up to 40 users) is $200 per year and it includes:

    Everything in the 'Standard' option plus:
  • Submit articles/announcements as often as you need, carefully edited and published on the site by our team of writers.
  • Reach thousands of daily CAN readers through articles and social media.
  • Join our Discord to publicise events, open calls or projects.
  • Your activities are boosted on our social media channels.
  • Your events are included in our public calendars.
  • We share ideas, networks, and resources with you.

You can also support CAN by donating

Click continue to donate with Stripe or you can also use PayPal, ETH, Bitcoin or Tezos

/++

/+