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

Maxime Plantady, Evelyne Drouin

Light projections on a sculpture based on facial expressions

Expression Detection

Bastien Girschig, Google Arts & Culture Lab

Use PoseNet to extract a pose and generate stick figure choreographies

UMAP, PoseNet

Tony Beltramelli

Translate image features from a graphical user interface to RNN generated website

Image Captioning, pix2code, RNN, LSTM, CNN

Synflux, Hatara

A GAN trained on 2 million birds and converted to double Jacquard knit format

GAN

Cunicode

A StyleGAN trained on thousands of public domain beetle illustrations

StyleGAN, GAN

David Young

Generate pictures of flowers with a GAN

GAN, DCGAN

Sofia Crespo

Add DeepDream like patterns on 3D beatles and print the new specimens

DeepDream, 3D

Shardcore

Apply First Order Motion to objects with faces

First Order Motion

Refik Anadol

Adjust a painting in real-time with a 3D point cloud and Face Tracking to create the illusion of a 3D painting

Face Tracking, Point Cloud

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

Katerina Malakhova

Visualize the latent representation of a grandmother in a CNN

CNN

Dan Motzenbecker and Kyle Phillips, Google Creative Lab

Classifies drawings and matches them with professional graphics

RNN, NNS

Christopher Hesse

Turn a drawing into a cat in a web browser

pix2pix, GAN

Zhihao Ouyang, Yihang Yin, Kun Yan, Jian Wu, Xiaolin Hu

Compose violin music with prompts trained with a combination of a CNN and RNN, and performed

RNN, CNN, rGMIR, Magenta

Helena Sarin

GAN trained on personal pictures of flowers

GAN

Erin Beesley

GAN trained on 10 thousand images of children's art

GAN

Sofia Crespo

CNN generated blend of corals

CNN

Diego Porres

GAN-generated Mexican and Guatemalan textiles

DCGAN, GAN

Emil Wallner

Use an image captioning model, pix2code, to translate design mockups into a website

Image Captioning, pix2code, RNN, LSTM, CNN

Mario Klingemann

Extract face markers with a camera and use a pix2pix model to translate the face markers to paintings

Camera, Face Alignment, pix2pix

Ross Goodwin, Oscar Sharp

An LSTM generated screenplay trained on sci-fi screenplays, and produced according to the screenplay

RNN, LSTM

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

Stefan Sietzen

Realtime Interactive Visualization of Convolutional Neural Networks in Unity

CNN, Unity

Christian Mio Loclair, Waltz Binaire

A computer looks at itself with a camera and translates image features into text with an RNN

Camera, CNN, RNN

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners