Tele-present Wind

Virtual Genetic Code

A Computer Vision System’s Walk Through Times Square

Video from deepython demonstrates an object recognition neural network framework applied to footage taken in New York:

This is a state of the art object detection framework called Faster R-CNN described here https://arxiv.org/abs/1506.01497 using tensorflow.

I took the following video and fed it through Tensorflow Faster R-CNN model, this isn’t running on an embedded device yet.

Link

Interactive Example Based Terrain Authoring with Conditional Adversarial Networks

Graphics research from LIRIS, Purdue University and Ubisoft is method of generating 3D landscape terrain from simple pen markings with the assistance of neural networks:

Authoring virtual terrains presents a challenge and there is a strong need for authoring tools able to create realistic terrains with simple user-inputs and with high user control. We propose an example-based authoring pipeline that uses a set of terrain synthesizers dedicated to specific tasks. Each terrain synthesizer is a Conditional Generative Adversarial Network trained by using real-world terrains and their sketched counterparts. The training sets are built automatically with a view that the terrain synthesizers learn the generation from features that are easy to sketch. During the authoring process, the artist first creates a rough sketch of the main terrain features, such as rivers, valleys and ridges, and the algorithm automatically synthesizes a terrain corresponding to the sketch using the learned features of the training samples. Moreover, an erosion synthesizer can also generate terrain evolution by erosion at a very low computational cost. Our framework allows for an easy terrain authoring and provides a high level of realism for a minimum sketch cost. We show various examples of terrain synthesis created by experienced as well as inexperienced users who are able to design a vast variety of complex terrains in a very short time. 

Link

Portal in AR looks amaaaazing!

Unfortunately this is just a demo on HoloLens by developer KennyW, but here’s hoping it comes to life one day.

Alternative Neural Edit

Latest project from @mario-klingemann employs Neural Networks trained on a collection of archive footage to recreate videos using the dataset.

It is confirmed that no human intervention has occured in the processed output, and it is interesting where there are convincing connections between the two (and where there apparently are none):

Destiny Pictures, Alternative Neural Edit, Side by Side Version 

This movie has been automatically collaged by an neural algorithm using the movie that Donald Trump’s gave as a present to Kim Jong Un as the template, replacing all scenes with visually similar scenes from public domain movies found in the internet archive. 

Neural Remake of “Take On Me” by A-Ha

An AI automatically detects the scenes in the source video clip and then replaces them with similar looking archival footage. The process is fully automatic, there are no manual edits.

Neural Reinterpretation of “Sabotage” by the Beastie Boys

An AI automatically detects the scenes in the source video clip and then replaces them with similar looking archival footage.

There are other video examples at Mario’s YouTube page (but some may not be viewable due to music copyright.

If you follow Mario’s Twitter timeline, you can get updated with the latest examples, and follow the evolution of the project [link]

slide the light off you you may find some peace

FontCode

Research from Columbia Computer Graphics Group can create textual encryption by minute altering of font characteristics using neural networks:

We introduce FontCode, an information embedding technique for text documents. Provided a text document with specific fonts, our method embeds user-specified information in the text by perturbing the glyphs of text characters while preserving the text content. We devise an algorithm to choose unobtrusive yet machine-recognizable glyph perturbations, leveraging a recently developed generative model that alters the glyphs of each character continuously on a font manifold. We then introduce an algorithm that embeds a user-provided message in the text document and produces an encoded document whose appearance is minimally perturbed from the original document. We also present a glyph recognition method that recovers the embedded information from an encoded document stored as a vector graphic or pixel image, or even on a printed paper. In addition, we introduce a new error-correction coding scheme that rectifies a certain number of recognition errors. Lastly, we demonstrate that our technique enables a wide array of applications, using it as a text document metadata holder, an unobtrusive optical barcode, a cryptographic message embedding scheme, and a text document signature.

More Here

the clicking sound of the rack is oddly satisfying.

https://instagram.com/p/BQIDI5eh5_m/

I can not argue with that

This house is being 3-D printed with human and robot construction. Mesh mould technology uses the precision of robot building capacities to eliminate waste.

follow @the-future-now