AI data paintings & sculptures
Virtual Gallery
Refik Anadol Studio

Please select the video quality:

A.I. Initializing...
Refik Anadol Studio
Virtual Gallery
Urban Dreams
Space Dreams
Nature Dreams
Auto
Fixed
Machine Hallucinations

- Urban Dreams -

In Urban Dreams, Anadol offers new insights into the repre sentational possibilities emerging from the intersection of advanced technology, urban memory, and contemporary art. The work uses over 100 million images from the cities of New York and Berlin, focusing specifically on typical public spaces. The content is used to train a StyleGAN2 to identify and learn patterns hidden in urban scenery, showcasing how the elusive process of memory retrieval transforms into data collections.

Machine Hallucinations

- Space Dreams -

Space Dreams transforms a vast data set of 1.2 million images captured from the International Space Stations (ISS), along with additional satellite images of Earth's topology, into a dynamic data painting. Each version of the machine's dream sequences is derived from a different generative adversarial network (GAN) latent walk, exploring artificial intelligence's capacity to reach its own subconscious and offering an avant- garde form of cartographic aesthetics.

Machine Hallucinations

- Nature Dreams -

Nature Dreams is a series of synesthetic reality experiments based on Style GAN 2 algorithms, utilizing over 69 million images of National Parks, Iceland, and other natural wonders to train a generative model for the machine to dream about the most mesmerizing features of our Mother Nature. This transformation of the data collection becomes not just a means of visualizing information, but also a transmutation of our desire for experiencing nature into a poetic visual.

Machine Hallucinations

- Urban Dreams -

Machine Hallucinations

- Space Dreams -

Machine Hallucinations

- Nature Dreams -

Credits

Refik Anadol Studio

Refik Anadol (b. 1985, Istanbul, Turkey) is a media artist, director, and pioneer in the aesthetics of machine intelligence. His body of work locates creativity at the intersection of humans and machines. In taking the data that flows around us as his primary material and the neural network of a computerized mind as his collaborator, Anadol paints with a thinking brush, offering us radical visualizations of our digitized memories and expanding the possibilities of architecture, narrative, and the body in motion. Anadol's site-specific parametric data sculptures, live audio/visual performances, and immersive installations take many forms, while encouraging us to rethink our engagement with the physical world, its temporal and spatial dimensions, and the creative potential of machines.

  1. Alex Morozov
  2. Carrie He
  3. Danny Lee
  4. HyeJi Yang
  5. Efsun Erkilic
  6. Ho Man Leung
  7. Julia Thompson
  8. Kerim Karaoglu
  9. Kyle McLean
  10. Nicholas Boss
  11. Nidhi Parsana
  12. Pelin Kivrak
  13. Raman K. Mustafa
  14. Toby Heinemann

Lusion

Lusion is an award winning multidisciplinary production studio. From creative to production, we collaborate with creative agencies and design studios to deliver compelling, real-time experiences, which go far beyond expectations.

We help Refik Anadol Studio to design and develop this immersive web experience during the Covid-19 pandemic for the Nvidia GTC 2020 conference.

Follow us

wwwtwinigfb

Process

01.

Machine Hallucinations is an ongoing project of data aesthetics based on collective visual memories of space, nature, and urban experiences. Since the inception of the project in 2016, our studio has been utilizing DCGAN, PCGAN and StyleGAN to train machine intelligence as collaborator to human consciousness in processing these vast datasets and unfolding unrecognized layers of our external realities. We collect data from digital archives and social media platforms and process them with machine learning classification models such as CNN's, Variational Autoencoders and deep ranking, filtering out noise and irrelevant data points. The sorted image datasets are then clustered into thematic categories to better understand the semantic context of the data universe.

02.

This expanding data universe not only represents the interpolation of data as synthesis, but also becomes a latent cosmos in which hallucinative potentiality is the main currency of artistic creativity. In order to capture these hallucinations from a multi-dimensional space, we use StyleGAN2, NVIDIA DGX Station, 500 TFLOPS of AI power, and the world's fastest workstation for leading-edge AI research & development. StyleGAN2 generates a model for the machine to process the archive and the model is trained on subsets of the sorted images, creating embeddings in 4096 dimensions. To understand this complex spatial structure visually, we utilize dimensional-reduction algorithms, such as cuml-UMAP, projecting to a navigable 3-dimensional universe. This projection enables the audience to use an interactive browser to virtually fly around this latent space and record their own journeys.

03.

The final stage of production reveals Refik Anadol Studio's pioneering work in machine-generated aesthetics and synesthetic perception through various forms of data paintings, sculptures, and latent cinematic experiences. Fluid dynamics has been a source of artistic inspiration for Anadol since the inception of Machine Hallucinations. The studio's exploration of digital pigmentation and light through fluid solver algorithms accelerated by GPU computation and real time ray traced lighting made possible by NVIDIA RTX GPUs manifests this inspiration from the most innovative way available to multimedia artists. As a masterfully curated multi-channel experience, Machine Hallucinations brings a self-regenerating element of surprise to the viewers and offers a new form of sensational autonomy through cybernetic serendipity.