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

Anna Ridler, Ben Heim

Organise personal art collection with t-SNE, compose music according to each clusters, and detect each clusters with a camera to play corresponding music

t-SNE, CNN, Classification, Camera, Device

Fabin Rasheed

Translate a painting to a real-world photograph with GauGAN

GauGAN, GAN

Kevin Ho, Google Creative Lab

Measure the distance between CNN features to pair fonts

RNN, NNS

Jia-Bin Huang

GAN to generate machine learning papers

GAN

Eric Anderson

StyleGAN trained on plasma photos, displayed in a collage

StyleGAN, GAN

Scott Eaton

Custom pix2pix HD turning sketches into sculptures

pix2pix, GAN

Christine Payne

A music generator trained on hundreds of thousands of MIDI files and trained with GPT-2

GPT

Mario Klingemann

Turn finger drawings into a GAN generated image

pix2pix, Camera, GAN

Yuxi Liu

A robot that uses a camera and translates the image feature to RNN features, and writes poems on the beach

RNN, CNN, Image Captioning

Jonathan Fly

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

Depth Map, Point Cloud

Parag K. Mital

Mining Unlabeled Electronic Music Databases through 3D Interactive Visualization of Latent Component Relationships

Feature vectors

Magenta

Translating everyday sounds into instruments with Magenta's Differentiable Digital Signal Processing

DDSP, Magenta

Gene Kogan, Jeff Snyder

Finger pressure sensors, a breath pressure and embouchure sensor on the mouthpiece mapped with an ANN to generate sound via a microcontroller

Device, microcontroller, openFrameworks, ANN

Nye Thompson

Scene classification from surveillance cameras, clustered, visualized, and printed

CNN

Guillaume Slizewicz

A mobile broadcasting robot using MobileNet V2 trained on COCO, OCR, and text to speech to amplify messages in public spaces

OCR, Text-to-speech, COCO, MobileNetV2

Ben Snell

A 3D-GAN trained on sculptures inspired by the influence of nature and nurture

GAN, 3D

Jonathan Fly

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

SinGAN, GAN

Esteban Salgado

A StyleGAN trained on a dataset synthesised with analog and digital materials

GAN, StyleGAN

Ryosuke Tanno

GAN generated images of Japanese Anime Food I

GAN

Obvious

GAN generated Japanese wood prints, and then print them using the same technique

GAN

Shardcore

First Order Motion applied to Francis Bacon's Figure With Meat using a video of Boris Johnson

First Order Motion

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

Golan Levin, Lingdong Huang

A collection of “ambigrammatic” images, generated with a GAN, legible as faces in both upside-down and right-side up orientations

GAN, StyleGAN2, Super-resolution

Ross Goodwin

Use an N-gram model to generate 10 000 sonnets trained on works by William Shakespeare

N-gram

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners