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

Jason Antic

Colorize the B&W movie Metropolis with a pix2pix U-Net

U-net, Resnet, ImageNet, pix2pix, DeOldify

Massive Attack, Mario Klingemann

GAN generated music video

GAN

Ross Goodwin, Oscar Sharp

An LSTM generated screenplay trained on sci-fi screenplays, and produced according to the screenplay

RNN, LSTM

Eric Lu

Classify a photo and match it with a doodle

CNN, Classification

Yotam Mann

A WaveGAN-inspired model trained on the acapella vocal ensemble in Košice, Slovakia, translating Glenn Gould's piano into a Gregorian Choir

WaveGAN, GAN

OpenAI

Create images from text captions using GPT-3 and trained on 400M text–image pairs

DALL·E, GPT

Baum & Leahy

Blend sounds from Wavenet trained on field recordings, and NSynth tuned on nature sounds from British Library Wildlife and Environmental Sounds archive

Magenta, VAE, NSynth, Wavenet

Parag K. Mital

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

Corpus-based synthesis

Jules LaPlace

An RNN trained on cattle auctioneers

RNN

Gavin Shapiro, Jeremy Torman, cYsmix

Artistic Style Transfer for video applied to dancing flamingos in a recursive loop

Video StyleTransfer

Mike Tyka

Class visualization of insects with DeepDream

DeepDream, Gradient Ascent

Jonathan Fly

Apply GauGAN on Charlie Chaplin dressed as a tree

GauGAN, GAN

Google Arts & Culture Lab, Cyril Diagne

Take a selfie, extract the CNN features, and match them with features from portraits

CNN, NNS, Camera

Helena Sarin

SNGAN trained on doodles and upscaled and colorized with CycleGAN

GAN, CycleGAN, SNGAN

Maxime Lefebvre

GAN generated roman theatre projected on moving tiles

GAN

Jonathan Fly

A CNN model that extracts depth maps from artworks and then augment them in a 3D point cloud

Depth Map, Point Cloud

Jürgen Schmidhuber, Douglas Eck

Blues Improvisation with an LSTM

RNN, LSTM

Kishi Yuma

GAN interpolation inspired by Francis Bacon

GAN

Google AI

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

RNN, NNS

Emil Wallner

Use an image captioning model, pix2code, to translate design mockups into a website

Image Captioning, pix2code, RNN, LSTM, CNN

Libby Heaney

Pass the pixels of a frame through a Quantum Computer and track the transition with Open Pose

Quantum Computer, Open Pose, CNN

Es Devlin, Ross Goodwin, IYOIYO, Google Arts & Culture Lab

Generate a poem from a word and project it on your face

RNN, Camera

Sofia Crespo

CNN generated blend of corals

CNN

Ryan Murdock

Use BigGAN and CLIP-based Gradient Ascent to generate an image of "a horse head with four eyes"

BigGAN, Gradient Ascent, CLIP

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners