Collection: Residual

30 pieces
  • A Moment, 2019
    A Moment, 2019
    Regular price
    €59.99
    Sale price
    €59.99
    Unit price
    per 
  • Black and White, 2019
    Black and White, 2019
    Regular price
    Sold
    Sale price
    €199.99
    Unit price
    per 
  • Blind, 2019
    Blind, 2019
    Regular price
    €89.00
    Sale price
    €89.00
    Unit price
    per 
  • Colors of Life, 2019
    Colors of Life, 2019
    Regular price
    €64.10
    Sale price
    €64.10
    Unit price
    per 
  • Freedom, 2019
    Freedom, 2019
    Regular price
    Sold
    Sale price
    €89.90
    Unit price
    per 
  • Hide and Seek, 2019
    Hide and Seek, 2019
    Regular price
    Sold
    Sale price
    €199.99
    Unit price
    per 
  • Don't Leave Me, 2019
    Don't Leave Me, 2019
    Regular price
    €59.99
    Sale price
    €59.99
    Unit price
    per 
  • Don't Say a Word, 2019
    Don't Say a Word, 2019
    Regular price
    €59.90
    Sale price
    €59.90
    Unit price
    per 
  • Dawn, 2019
    Dawn, 2019
    Regular price
    €199.99
    Sale price
    €199.99
    Unit price
    per 
  • Dream, 2019
    Dream, 2019
    Regular price
    €145.90
    Sale price
    €145.90
    Unit price
    per 

Residual

What will we leave to future generations? portraits of machine dreaming about animals that once inhabited Earth? Is this the only way to remember them, just a residual memory? 

An exploration of anxieties around the wildlife such as global warming, destroyed habitat, shortage of food, and human predatory practices. Our exclusive artist, diavlex, uses AI as a tool of expression to represent the residual image of  species affected by human predatory actions.

TL;DR of Our Approach

  • The core AI technique for this collection is our Neural Painter implementation from scratch. Neural Painters, introduced in [1], are Generative Models models able to paint using brushstrokes, in contrast to common pixel-level ones. We consider Neural Painters to be a more natural choice for Art+AI artwork and, therefore, our preferred choice.

  • We also use a tailor-made Non-Adversarial Super-Resolution model based on a dynamic U-Net architecture [2]. The approach is inspired by fast.ai's 'Decrappification' technique [3]. 

---

References

[1] Neural Painters: A Learned Differentiable Constraint
for Generating Brushstroke Paintings. Reiichiro Nakano. Preprint. 2019. https://arxiv.org/abs/1904.08410

[2] U-Net: Convolutional Networks for Biomedical Image Segmentation. Olaf Ronneberger, Philipp Fischer, Thomas Brox. Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, LNCS, Vol.9351: 234--241, 2015, available at arXiv:1505.04597

[3] Decrappification, DeOldification, and Super Resolution
Jason Antic (Deoldify), Jeremy Howard (fast.ai), and Uri Manor (Salk Institute). 2019. https://www.fast.ai/2019/05/03/decrappify/