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

Derrick Schultz

Next frame prediction with a Conditional GAN, Super-resolution, and Super Slo-Mo on a fish

pix2pix, Super-Resolution, Super Slo Mo

Kishi Yuma

GAN interpolation

GAN

Sey Min

Take a selfie and use a CNN to determine how likely you are to be a k-pop star

CNN, Classification

Mario Klingemann

Create a deep fake with Kellyanne Conway's by translating face markers into a video of a person speaking

GAN, pix2pix

Memo Akten

RNN model trained on sounds and morphing trajectories in latent space z

Grannma Magnet, RNN

Maryna Taiberman, Meredith Thomas

Train GAN on maps and project on naked bodies

GAN

Fabin Rasheed

Give Google's voice assistant a StyleGAN face in VR and animate answers with First Order Motion

StyleGAN, GAN, VR, First Order Motion

Joel Simon

Use a word vector to generate an image, and a discriminator to detect the word vector from the generated image, similar to a GAN

GAN, cDCGAN

Synflux, Hatara

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

GAN

Gael Hugo, Google Arts & Culture Lab

Cluster books with UMAP and create imaginary islands to visualize them

UMAP

Stanislas Chaillou

StyleGAN interpolation, trained on Karl Blossfeldt's herbarium (1928)

StyleGAN

Gene Kogan

Apply Cubist Style Transfer live with a camera

StyleTransfer, Camera

Anne Spalter

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

Style Transfer, GAN

Lulu xXX, STORROR

Use Detectron2 to identify people in STORROR's parkour video and apply Optical Flow based Style Transfer

Detectron2, Optical Flow, StyleTransfer, deepflow

Eric Lu

Classify a photo and match it with a doodle

CNN, Classification

Mario Klingemann, Mr.doob

AI doodles in Mr.doob's multi-user drawing tool

RNN, QuickDraw

Jonas Jongejan, Henry Rowley, Takashi Kawashima, Jongmin Kim, Nick Fox-Gieg, Google Creative Lab

A user is challenged to draw an object and a CNN model tells if you are correct

CNN, Classification

Josh Nimoy

DeepDream inspired by Classical Western Art History

DeepDream, Gradient Ascent

Mayukh

Optimize the input image to maximize activations of a certain channel inspried by Olah, et al

Gradient Ascent

Nadine Lessio

Use Alexa voice assistants and add heuristics for it to disagree

Voice Detection, IoT, Hardware

Obvious, Nike

Train a GAN on Nike shoes, generate an image, and produce a shoe collection according to the generated image

GAN

Amber Frid-Jimenez

RNN generative piano music inspired by Satie

RNN

Sarah Meyohas

A GAN trained on a personal dataset of 100k individual petals and interpolated in a collage

GAN

Vadim Epstein

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

GAN, Animating Landscape

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners