Artistic Style-Transfer is getting good, fast

Gepostet vor 1 Jahr, 2 Monaten in #Design #Misc #Tech #AI #Art #Coding #Creativity

Share: Twitter Facebook Mail

Die Artistic Style-Transfer-Algorithmen werden immer besser, das psychedelic Kitten und die Matrix-Cat unten rechts ist tatsächlich ziemlich mindblowing. Die Pics stammen aus einem neuen Paper von Roman Novak und Yaroslav Nikulin: Improving the Neural Algorithm of Artistic Style.

artstyletransfer

Dazu gibt's eine neue Spielart namens Neural Doodle, damit kann man schon sehr bald mit ein paar groben Strichen im Stil von whoever malen, hier ein Browser-Toy von Dmitry Ulyanov dazu.

doodLast year, with Deep Dream (June 2015) and Style Networks (August 2015), the idea that deep learning may become a tool for Art entered the public consciousness. Generative algorithms based on Neural Networks so far haven’t been the most predictable or easiest to understand, but when they work — by combination of skill or luck — the quality of the output is second to none!

It took until 2016 for those techniques to be turned into tools that are useful for artists, starting with this paper we call Neural Patches (January 2016) that lets the algorithm process images in a context-sensitive manner. Now, when style transfer techniques are extended with controls and annotations, they can process images in a meaningful way: reducing glitches and increasing user control. This is our work on Semantic Style Transfer (March 2016), which can be applied to the same applications as before, as well as generating images from rough annotations—a.k.a. doodles.

AI-Animations with human Sounds

Google vor ein paar Tagen so: „Yay, wir haben hier 'ne neue AI-based Animation-Tech, hooray!“ (Paper) Hayayo Miyazaki über AI-based…

Frankenstein vs Ingmar Bergman: Persona and the Monster

Fascinating (and awesome and gory) Movie-Mashup from Filmscalpel: „In 1816, Mary Wollstonecraft Shelley began writing what was to become her…

Visual AI-Spaces Auto-Pilot

Ich habe schon ein paar mal über Mario Klingemanns Arbeiten hier gebloggt, derzeit jagt er Neural Networks durch Feedback-Loops und…

Synthesizing Obama from Audio

Im Mai bloggte ich über ein damals noch nicht veröffentlichtes Paper zur SigGraph2017, in dem sie eine Methode für generative…

Stereographic Torus Knot

I'm not sure what's going on here but I like it: „This is very similar to Rise Up, though with…

Moarph

Mario Klingemann does some weird shit again with CycleGAN Feedback Loops (Neural Networks feeding their results back to each other).…

Beautiful set of rules for artful learning

Ganz wunderbare Regeln für Schüler und Lehrer von Sister Corita Kent aus ihrem 1992er Buch Learning by Heart: Teachings to…

GATS on Driftwood and Skateboards from the 60s

Love the new GATS-Exhibit at Spoke Art featuring his bold Characters and Faces on Driftwood and Skatedecks from the 60s.…

3D-Rendering accepted as ID-Photo

Herr Raphaël Fabre hat ein 3D-Rendering als Passfoto eingereicht und ist damit durchgekommen. An den Haaren hätten sie's eigentlich erkennen…

3D-Visualized Typography-Ideaspace

Ich habe schon einige AI-Visualisierungen von Fonts gesehen, also sortierte Abbildungen des visuellen Idea-Space der Zeichensätze (also genau wie Skateboards…

Freddie and Bruce and the Scream

So, the funny Actionfigureshenaniganstweetoh すえきち‏ @suekichiii bought Edvard Munchs Der Schrei and he's obviously having a good time.