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

Bjørn Karmann, Google Creative Lab

A CNN model in a device that collects data and is auto trained to make an action

CNN, Hardware

Daniël Korssen

Create a shared playlist on Spotify and create a digital dance party by animating each dancer with PoseNet

PoseNet

Alsino Skowronnek

A StyleGAN trained on thousands of frames of a filmed sequence of images of graffiti from NYC in the late 70s/early 80s. The output is interpreted into a painting and an AR filter

StyleGAN

Nathan Shipley, Bella Poarch

Using StyleGAN transfer learning and layer blending to create a cartoon of Uma Thurman and then animating her using First Order Motion with a video of Bella Poarch from TikTok

StyleGAN, First Order Motion, GAN

Anna Ridler

A voiceover via a CNN and RNN for Walt Disney's Nature's Half Acre (1951) trained on text from female protagonists in romance novels

RNN, LSTM, CNN

Kaoru Okomura, Mike Tyka

Flora and fauna themed DeepDream projection on Kaoru Okomura

DeepDream

Eric Lu

Classify a photo and match it with a doodle

CNN, Classification

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

Jürgen Schmidhuber, Douglas Eck

Blues Improvisation with an LSTM

RNN, LSTM

Parag K. Mital

Corpus-based visual synthesis applied to Miley Cyrus's Wrecking Ball

Corpus-based synthesis

Google Brand Studio

Use a camera to find objects and a CNN identifies if it's correct

Camera, CNN, Classification

Jason Antic

Colorize B&W picture of Detroit with a pix2pix U-Net

U-net, Resnet, ImageNet, pix2pix, DeOldify

Cyril Diagne, Nicolas Barradeau, Simon Doury, Google Arts & Culture Lab

Map artworks with t-SNE

t-SNE, CNN

Gene Kogan

A Conditional GAN applied on satellite images from OpenStreetMap

pix2pix

Memo Akten

RNN model trained on sounds and morphing trajectories in latent space z

Grannma Magnet, RNN

Bob L. Sturm

RNN generated Gaelic folk music

RNN

Alexander Mordvintsev

Style Transfer based on Ernst Haeckel's art and a picture of Darwin

Style Transfer

Vadim Epstein

Music video, created with Feature Inversion (successor of DeepDream) and enhanced with Neural Video Interpolation (slow motion).

DeepDream inversion, Video interpolation

Christian Mio Loclair, Waltz Binaire

A computer looks at itself with a camera and translates image features into text with an RNN

Camera, CNN, RNN

Pindar Van Arman

Generate art with a camera and robot arm

CNN, Hardware

Sofia Crespo

CNN generated blend of of birds

CNN

Zihou Ng

A browser-based exploration of real-time latent space navigation of GAN at higher resolutions with WebGL

GAN

Fadi Al-Ghawanmeh and Kamel Smaïli

Translating voice to RNN generated MIDI files to improvise Arab maqamic music in real-time

CNN, RNN

Jonathan Fly

Apply Ken Burns 3D until it breaks, exposing the simulation software the model was created with

Ken Burns 3D, GAN, Inpainting

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners