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

Yuguang Zhang

A GAN trained on the artists sleeping patterns and then interpolated by a custom sheet folding machine

GAN, Hardware

Erin Beesley

GAN trained on 10 thousand images of children's art

GAN

Lulu xXX

Clustering of Static-Adaptive Correspondences for Deformable Object Tracking (CMT), with Optical Flow enhanced Style Transfer, and a loop generating algorithm based on Optical Flow

CMT, StyleTransfer, Optical Flow, deepflow

Jason Antic

Colorize B&W livingroom in Sweden with a pix2pix U-Net

U-net, Resnet, ImageNet, pix2pix, DeOldify

Scott Eaton

Custom pix2pix HD turning sketches into bodies

pix2pix, GAN

Google Arts & Culture Lab

Use a camera and CNN to classify artworks in an exhibition

CNN, Classification

Egor Kraft

A GAN trained on a thousand blots of ink splashed onto watercolour paper and interpolated live on electronic ink screens

GAN

Billie Eilish, Google Creative Lab, YouTube Music, IYOIYO, Plan8

An interactive, gradient-based audio and video alignment of thousands of covers of Billie Eilish’s “Bad Guy”

Memo Akten

Translate objects and hand movements to nature scenes with a Conditional GAN

pix2pix, GAN

Sterling Crispin

A Facial Recognition model guides a 3D genetic algorithm to create a mask. The masks are 3D-printed with nylon

Facial Recognition, Genetic Algorithm

Naofumi Akimoto

Create a video with a conditional GAN using next frame predictions

GAN, pix2pix

Lulu xXX, Jacob Sutton

Apply Slic Superpixels and Style2Paint to Jacob Sutton's music video

Style Transfer

Memo Akten

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

Word2Vec

Magenta, Google Creative Lab

Making music using new sounds generated with machine learning

RNN

Sofia Crespo

Lenticular print of images made with a CNN

CNN, Lenticular Print

Gene Kogan

DCGAN trained on a database of handwritten Chinese Characters

DCGAN, GAN

Kishi Yuma

GAN trained on pictures of hands

GAN

DataDada

Train a model to map a gesture to a sound

PoseNet

Refik Anadol

A StyleGAN trained on 100 million pictures of New York; the GAN-generated images are then animated with Point Advection in Houdini

GAN, Houdini, ESR-GAN, StyleGAN

Vadim Epstein

Self-Supervised Learning of Decoupled Motion and Appearance for Single-Image Video Synthesis applied to a collage of buildings

GAN, Animating Landscape

Minne Atairu

A StyleGAN model trained on portraits

StyleGAN, GAN

Boris Boege

Portrait generating GAN

GAN

Vadim Epstein

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

DeepDream inversion, Video interpolation

Cunicode

A StyleGAN trained on thousands of public domain beetle illustrations

StyleGAN, GAN

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners