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

Monolesan

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

PoseNet, Camera, TensorFlow.js

Parag K. Mital

Corpus-based visual synthesis recreating the Simpsons intro with the intro from the Family Guy

Corpus-based synthesis

Nathan Shipley, Bobbo Andonova

Translate Bobbo Andonova's live sketch video to a person with Pixel2style2pixel, a StyleGAN Encoder for Image-to-Image Translation

Pixel2style2pixel

David Ha, Jonas Jongejan, Ian Johnson, Google Creative Lab

An RNN model generates doodles based on your style

RNN

Anne Spalter

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

Style Transfer, GAN

Fadi Al-Ghawanmeh and Kamel Smaïli

Translating voice to RNN generated MIDI files to improvise Arab maqamic music in real-time

CNN, RNN

Vibert Thio, Douglas Eck

An interactive room where you can create music with Magenta's javascript version of MusicVAE and MelodyRNN

Magenta, VAE, RNN

Google Creative Lab, Google Arts & Culture Lab, IYOIYO

Match a user generated drawing with paintings, by extracting the features of the outline of an image and paring it with the drawings

NNS, Edge Detection, CNN

Anna Ridler

GAN collage of blooming tulips trained on the artist's photos of tulips

GAN

Lulu xXX

DJ video with video texture advection with flipfluids and Optical Flow based Style Transfer

StyleTransfer, Optical Flow, deepflow

Item 1 of 2

Nuntinee Tansrisakul, Yuguang Zhang

A GAN-generated video is rendered with a digital pinhole camera process, the negatives are printed, and then processed in a darkroom to restore the aesthetic of analog photos in a digital-first world

GAN

Google Creative Lab

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

PoseNet, Camera

Vivian Troya

Two devices that transcribe voice in real-time and an RNN-based model that predict future conversations

RNN, Device, Microphone

Javier Ideami

Visualizing the loss landscapes with real data using ResNet 20 architectures with batch sizes of 16 and 128 and the Adam optimizer

Loss, ResNet, Adam

Nao Tokui

Turn images into sound by matching CNN features with CNN features of audio files

CNN, NNS

Xavier Snelgrove

Create a texture by combining two images with Style Transfer

Style Transfer, Texture synthesis

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

Louise Macfadyen

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

GAN, RunwayML

Orkhan Mammadov, Vadim Epstein

Recurrent application of Style Tranfer, then processed by ProGAN

ProGAN, Multi-Style Transfer

Jack Qiao

Generate font combinations by matching the CNN features of fonts

NNS, CNN

Item 1 of 3

LIA

Using Chimera Painter to turn scribbled monsters into real monsters

Chimera Painter

Kishi Yuma

GAN interpolation

GAN

Max Braun

A StyleGAN trained on eBoy's database of pixel art

GAN

Sougwen Chung

Train an RNN on drawing motions and create a painting in collaboration where the model has one color and Sougwen Chung has another

RNN, LSTM

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners