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

Use Deep Painterly Harmonization to add objects to famous paintings

Deep Painterly Harmonization

Bastien Girschig, Romain Cazier, Google Arts & Culture Lab

Match a user-generated shape with paintings; the CNN features of the shapes are matched with a database of features of outlined artworks

NNS, Edge Detection, CNN

Manny Tan, Kyle McDonald, Google Creative Lab

Thousands of bird sounds visualized using an RNN model

RNN

Guillaume Slizewicz

Create scenery descriptions from a camera input with Google's vision API and K-means, and then use an LSTM model to write the descriptions

LSTM, K-means, CNN

Steve Savage

Self-organising textures of fruits using Neural Cellular Automata

Self-organising textures, Neural Cellular Automata

Helena Sarin

SNGAN trained on doodles and upscaled and colorized with CycleGAN

GAN, CycleGAN, SNGAN

Google Creative Lab

Extract the pose from a picture and match it with an image with the same pose

PoseNet, Camera

Stephanie Dinkins

An RNN trained on oral histories from three generations of women from a single-family to highlight concerns of people who are underrepresented in the tech sector, displayed with an interactive voice assistant

RNN, LSTM, Microphone

Alexander Mordvintsev

Visualize features in a neural network using Gradient Ascent

CNN, Activations

Dani Joy

An overpainted GAN interpolation of a smoking monkey

GAN

Andy Matuschak, Google

A real time implementation of Sketch RNN which predicts future strokes while you draw

RNN, QuickDraw

Memo Akten

Pick random words from Word2Vec and look at their relationships to the words ‘man’ and ‘woman’

Word2Vec

Nushin Isabelle Yazdani

Generative images of convicts using a GAN

GAN

Lisha Li, Vladimir Glazachev, Dzmitry Pletnikau, Eric Liu

Automatically animate digital humans or your digital double with just text or speech

Text to Animation of Virtual Characters

Bastien Girschig

Censor inappropriate Bible sections

Text classification

Matty Mariansky

A curve generator is pitted against a face recognition algorithm. Using an evolutionary process, the curves thrive to be more and more face-like

CNN, Face Detection

Hans Brouwer

Audio-reactive latent interpolation with StyleGAN2 created by modulating latent and noise inputs with musical features

StyleGAN2

Ardavan Bidgoli, Pedro Veloso

VAE-generated 3D point clouds for different objects, interpolated with a MIDI controller

VAE, Hardware, Point Cloud

Eric Lu

Classify a photo and match it with a doodle

CNN, Classification

Lulu xXX, STORROR

Use Detectron2 to identify people in STORROR's parkour video and apply Optical Flow based Style Transfer

Detectron2, Optical Flow, StyleTransfer, deepflow

Eric Anderson, Latentspaceman

A StyleGAN interpolation inspired by Watchmen's Doctor Manhattan on a lenticular print

StyleGAN, Lenticular, GAN

Gene Kogan

Visualize the layers of a CNN with your camera

CNN, Camera

Anne Spalter

A GAN-generated highway image with Style Transfer from a charcoal drawing

Style Transfer, GAN

Anne Spalter

An image with circles Style Transferred with pictures of three airplanes using Nightcafe, and the spaceman and asteroid are animated with Plotaverse

Style Transfer

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners