00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

Everyday Experiments

Everyday Experiments

How will tomorrow’s technologies redefine the way we live at home?

Themes

Through a range of experiments in a set of unique themes, we explore ways to enhance our interactions with space and improve our everyday lives.

Explore Theme

Sustainability + Circularity

Re-imagining life at home within the boundaries of our planet.

1 New experiment

Explore Theme

Lifestyle + Well-being

Exploring new ways to see and use our homes to elevate our mood and well-being.

6 New Experiments

Explore Theme

Privacy + Trust

Challenging the way we think about safety and security at home.

4 New Experiments

Explore Theme

Play + Learn

Transforming the home into a playground for creativity and learning.

Explore Theme

Design + Organize

Finding novel ways to make the most out of what we already have.

Neverending Catalogue

GAN
Procedurally Generated Content

What if generative algorithms could dream up your new bedroom?

Built by — Philip Pries Henningsen

Philip is a machine learning engineer who enjoys working with natural data and problems. By that, I mean problems that are directly relatable to humans — such as vision, audio, language etc. For the last four years, I have mainly worked with computer vision problems, which is anything that involves understanding images or video.

Neverending Catalogue is a technical prototype which would create computer-generated bedrooms to act as an inspiration database, essentially taking on the role of an interior designer for you to consult at your leisure.

00:00 / 00:00

Latent space walk from the final stage of the self-trained model

'Artificial intelligence, or AI, is getting a lot of attention these days, but I think it’s much more interesting to talk about IA:  intelligent assistance.'

—Philip Pries Henningsen

It involves using generative adversarial networks (GANs)  to generate images of completely new bedrooms using pre-existing photographs of rooms lifted from the IKEA catalogue. This experiment tried to answer the questions: Is there a particular "IKEA style" for decorating a room? And can a machine learning model understand it and generate new rooms?

00:00 / 00:00

Latent space walk from 3rd training round

'Everyone knows the feeling of being stuck in a problem – classically creative or otherwise – and having no ideas of how to solve it. Can technology like this help us think outside the box and solve problems in new ways?'

—Philip Pries Henningsen

Images of bedrooms are trained on top of a generative adversarial network (GAN) which has already been exposed to thousands of generic bedroom images. The result is that the images created by the network are flawed, but beautifully so. This is exciting. An application of a model like this could be used by those looking to re-decorate, or even to give interior decorators or designers new ideas on what to do with a room and furniture. Even with obvious errors, the wild, unpredictable scenes the algorithm is capable of dreaming up could still be used as inspiration.

Everyday Experiments is a project by SPACE10 & IKEA.

Next
Experiment

See Through the Eyes of a Computer

By navigating this website you agree to the storing of cookies as described in our terms of use.

OK

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

00:00 / 00:00

Everyday Experiments

Everyday Experiments

How will tomorrow’s technologies redefine the way we live at home?

00:00 / 00:00