Submit a Project

ML x ART

A showcase with creative machine learning experiments

👋 I'm Emil, a resident at the Google Arts & Culture Lab. I've curated this collection.

Year
Artist
Technology
Theme
Medium
Default order

Gene Kogan

Continuously zoom in a image and apply DeepDream and use Dense Captioning to label objects in the video

DenseCap, DeepDream

Mario Klingemann

Generate epigrams with GPT-2 and display them on vintage time table boards

Transformer, GPT

Lulu xXX, Noj Barke

Use photogrammetry to extract vector points from images, and apply a Optical Flow based StyleTransfer with Noj Barke's dot paintings

Photogrammetry, Optical Flow, StyleTransfer, deepflow

Sofia Crespo

CNN generated blend of of birds

CNN

Sougwen Chung

Train an RNN on drawing motions and create a painting in collaboration with a robot arm controlled by the model

RNN, LSTM

Maxime Lefebvre

GAN generated roman theatre projected on moving tiles

GAN

Google AI

Turn book paragraphs into an RNN features and match them with similar paragraphs

RNN, NNS

Eunsu Kang, Chun-Liang Li, Songwei Ge, Austin Dill, Lingyao Zhang, Manzil Zaheer, Barnabas Poczos

A 3D, DeepDream, GAN generated sculpture and printed, inspired by Homer’s Iliad

DeepDream, GAN, Point Cloud

Joel Simon

Generate an area to simulate Game of Life using CMA-ES, GAN, and CPPN, optimized to maximize their total life

GAN, CPPN, CMA-ES, Game of Life, Perlin Noise

Minne Atairu

A StyleGAN model trained on portraits

StyleGAN, GAN

Jonathan Fly

Use SinGAN to train a GAN with a single image, Frymire, the classic compression image

SinGAN, GAN

Jason Salavon

Combine a collage of GAN interpolations to create motives, then projected on a building

GAN

Alsino Skowronnek

A Conditional GAN trained on a data set of ~1,000 annotated street tag images from Germany. The model can generate new graffiti tags based on any textual input from the audience

Pix2Pix

Jia-Bin Huang

GAN to generate machine learning papers

GAN

Daniel Voshart

Using Artbreeder to translate statues of Roman emperors to latent vectors, and adjusting the vector to make them real

ArtBreeder, GAN, Photoshop

Memo Akten

Translate objects and hand movements to nature scenes with a Conditional GAN

pix2pix, GAN

Vadim Epstein

Recurrent application of Style Tranfer and 3D videomapping projected on building

StyleTransfer, Multi-Style Transfer

Christopher Hesse

Turn a drawing into a cat in a web browser

pix2pix, GAN

David Ha, Jürgen Schmidhuber

A neural net-generated environment where reinforcement learning agents learn

Reinforcement Learning, Mixture Density Networks, RNN, LSTM, CNN

Masaru Mizuochi

A collage with CPPN generated images

CPPN

Max Braun

A StyleGAN trained on eBoy's database of pixel art

GAN

Daniel Smilkov, Fernanda Viégas, Martin Wattenberg, the Big Picture team, Google Creative Lab

Generates a 3D t-SNE map to visualize high-dimensional data

t-SNE

Jessica In, George Profenza, Sam Price

A live, interactive drawing installation that facilitates collaboration between a human and a robot, the model is trained on the QuickDraw dataset and uses the QuickDraw Classifier, and a custom SketchRNN

Hardware, SketchRNN, QuickDraw, Classifier

Derrick Schultz

Next frame prediction with a Conditional GAN, Super-resolution, and Super Slo-Mo on a fish

pix2pix, Super-Resolution, Super Slo Mo

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners