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

Helena Sarin

SNGAN trained on doodles and upscaled and colorized with CycleGAN

GAN, CycleGAN, SNGAN

Lingdong Huang, Zheng Jiang, Giada Sun, Tong Bai, Eunsu Kang, Barnabas Poczos

Generate a vintage Chinese opera by extracting poses and augmenting them with a pix2pix model

pix2pix, RNN, LSTM, Markov Chain, OpenPose, Detectron

Elijah M

Using Portraitai and Deepart.io to create a style and then use EbSynth to apply it to a video

Portraitai, deepart.io, EbSynth, Style Transfer

Eyal Gruss, Ayelet Sapirshtein, Vered Heruti

A machine that creates live, generated, visual poetry from spoken poetry in any language

AttnGAN, Machine translation, Speech to text

Gavin Shapiro, Jeremy Torman, cYsmix

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

Video StyleTransfer

Alexander Mordvintsev

Use Style Transfer where the content comes from a face and the style from a video of clouds

Style Transfer

Google Creative Lab

Collect dataset and use AutoML to classify the images

AutoML, CNN, Hardware

Zaria Howard

Draw a face in VR and translate it to a real face with a Conditional GAN

pix2pix, VR, GAN

Refik Anadol

Extract CNN features from images and organize images with cuml-UMAP, create a device to explore the space with hand motions

cuml-UMAP

Steve Savage

Self-organising textures of fruits using Neural Cellular Automata

Self-organising textures, Neural Cellular Automata

Parag K. Mital

Corpus-based audio synthesis on Michael Jackson’s Beat It using Nature Recordings

Corpus-based synthesis

Golan Levin, David Newbury, Kyle McDonald, Irene Alvarado, Aman Tiwari, Manzil Zaheer

Select a region on a map and extract CNN features and use NNS to find similar regions

CNN, NNS

Dani Joy

Produce large scale Style Transfer-like artworks, print, and paint over

Style Transfer

Scott Eaton

Custom pix2pix HD turning sketches into bodies

pix2pix, GAN

Lulu xXX, Paradis

Apply Slow motion and fluid footage and Optical Flow based Style Transfer on Paradis's Recto Verso

StyleTransfer, Optical Flow, deepflow

Christine Sugrue, Google Arts & Culture Lab

Use Object Detection to explore details in artworks

CNN, Object Detection

Gene Kogan

Translate a live face to face trackers and turn them into a another person with Pix2pix

GAN, Pix2pix, Camera

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

Maxime Lefebvre

GAN generated roman theatre projected on moving tiles

GAN

Mario Klingemann, Simon Doury, Google Arts & Culture Lab

Find N artworks that link two artworks

CNN, NNS

Masaru Mizuochi

A collage with CPPN generated images

CPPN

Robbie Barrat

GAN-generated Renaissance paintings using the WikiArt dataset

GAN, DCGAN

Stefan Sietzen

Realtime Interactive Visualization of Convolutional Neural Networks in Unity

CNN, Unity

Erwin Driessens, Maria Verstappen

Using Face Recognition and a robot arm to find grains of sand that looks like faces

Face Recognition, CNN

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners