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

Emil Wallner

Colorize modern B&W photographs with a U-net

pix2pix, U-net

Vadim Epstein

Painting by Viktor Vasnetsov, animated with 'Animating Landscape' and Multi-Domain Multi-Modality I2I translation

Multi-Domain Multi-Modality I2I translation, Animating Landscape

Jennifer Walshe, Memo Akten

Train an audio RNN and GAN on Jennifer Walshe's video performances, and generate music and visuals real-time during a duet with the artist and model

Grannma Magnet, RNN, GAN

Minne Atairu

A StyleGAN model trained on portraits

StyleGAN, GAN

Erik Swahn

GAN trained on Defra's Lidar data of London, then visualize the height maps in Aeriolod

StyleGAN, GAN, Aeriolod

Hannu Töyrylä

Custom GAN-generated image with self-attention, trained on personal photos from Finland

GAN, Self-attention

Susie Rong Fu

A camera takes a photo and a Style Transfer model translates it into a sketch, while Susie Rong Fu makes a portrait of the same person

StyleTransfer, Camera

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

Ryan Murdock

Perceptual MinMax trained on 80 images from CelebA

Min-Max

Joel Simon

Generate an area to simulate Game of Life using CMA-ES, GAN, and CPPN, optimized to maximize their total life

GAN, CPPN, CMA-ES, Game of Life, Perlin Noise

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

Louise Macfadyen

A GAN trained on 3,600 wings from the Slater Museum

GAN, RunwayML

Jia-Bin Huang

GAN to generate machine learning papers

GAN

Cunicode

A StyleGAN trained on thousands of public domain beetle illustrations

StyleGAN, GAN

Robbie Barrat

Apply patches from artworks to a painting and guide it with a GAN discriminator

GAN, Discriminator, Inpainting

Pindar Van Arman

Generate art with a camera and robot arm

CNN, Hardware

Bill T. Jones, Google Creative Lab

Detect poses and voice and add the spoken words live in the choreography

PoseNet, Camera, Voice detection, Microphone

Google AI

Word association games powered by semantic search

Semantic search

Obvious

Storify and auction GAN generated paintings based on Robbie Barrat's model

GAN

Vít Růžička, Eunsu Kang, David Gordon, Ankita Patel, Jacqui Fashimpaur, Manzil Zaheer

RNN generated fake articles seeded by real-world article titles

RNN

Ziv Epstein, Matt Groh, Manuel Cebrian, Iyad Rahwan

Use GAN inpaintings to add spirits to videos

GAN, Inpainting

Google Research, Google Creative Lab, YouTube Music

Analyse voice files to match the similarity to Freddie Mercury

CNN, RNN, Classification, Magenta

Vadim Epstein

Recurrent application of Style Tranfer and 3D videomapping projected on building

StyleTransfer, Multi-Style Transfer

Monolesan

Using PoseNet to create art using your body parts like eyes, hands, chest and knees

PoseNet, Camera, TensorFlow.js

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners