Lucas deGomez

prostheticknowledge:

Augmented Reality in 10 Lines of HTML

Tutorial from Alexandra Etienne is a guide to create a simple Augmented Reality project with a marker and web browser coding editor:

Do you want to do Augmented Reality on the web ? You can now do it in 10 lines of HTML! Seriously! Let me walk you thru the code, it’s crazy simple.

We released AR.js recently. You can experience efficient augmented reality for the web directly on your phone without installing any applications. But let’s go further and see how to produce your own augmented reality experience. The shortest example of AR.js is only 10lines of HTML thanks to the magic of a-frame. You can see it live on codepen

More Here

youth80s:

<b>Pierrot le Fou</b> (1965), dir. Jean-Luc Godard

(via brunastonge)

prostheticknowledge:

Picture Window

Code from Ryan Sullivan can provide 3D first person perspective with a flat 2D monitor using tracking from an HTC Vive controller:

This is a Unity asset that allows you to turn your display (whether that’s a monitor, tv, or projected image) into a window that looks into the virtual space from the perspective of a tracked object. 

More Here

digg:

Watch A Robot With Perfect Penmanship Craft The Most Artful Letters

we always knew the calligraphy bot 9000 would eventually be invented. that’s why we gave up on learning cursive

prostheticknowledge:

SoundNet

Computer Science research from MIT CSAIL can recognize the content of video based on audio using neural networks:

We learn rich natural sound representations by capitalizing on large amounts of unlabeled sound data collected in the wild. We leverage the natural synchronization between vision and sound to learn an acoustic representation using two-million unlabeled videos. Unlabeled video has the advantage that it can be economically acquired at massive scales, yet contains useful signals about natural sound. We propose a student-teacher training procedure which transfers discriminative visual knowledge from well established visual recognition models into the sound modality using unlabeled video as a bridge. Our sound representation yields significant performance improvements over the state-of-the-art results on standard benchmarks for acoustic scene/object classification. Visualizations suggest some high-level semantics automatically emerge in the sound network, even though it is trained without ground truth labels. 

More Here

prostheticknowledge:

Neural Enhance

Proof of concept coding project from Alex J. Champandard can enhance details in images (like CSI or Blade Runner) using neural networks:

As seen on TV! What if you could increase the resolution of your photos using technology from CSI laboratories? Thanks to deep learning and #NeuralEnhance, it’s now possible to train a neural network to zoom in to your images at 2x or even 4x.  You’ll get even better results by increasing the number of neurons or training with a dataset similar to your low resolution image.

The catch? The neural network is hallucinating details based on its training from example images. It’s not reconstructing your photo exactly as it would have been if it was HD. That’s only possible in Holywood — but using deep learning as “Creative AI” works and its just as cool!

More Here

Blade Runner is almost here! O_O