Category: Code

Live Portraits

July 21, 2022 /

We have all seen deepfakes and how real they can seem, a group have taken it a step further and the resolution and small details like month and eye movement are really impressive.

A snippet from the website

“We propose a system for the one-shot creation of high-resolution human avatars, called megapixel portraits or MegaPortraits for short. Our model is trained in two stages. Optionally, we propose an additional distillation stage for faster inference.

Our training setup is relatively standard. We sample two random frames from our dataset at each step: the source frame and the driver frame. Our model imposes the motion of the driving frame (i.e., the head pose and the facial expression) onto the appearance of the source frame to produce an output image. The main learning signal is obtained from the training episodes where the source and the driver frames come from the same video, and hence our model’s prediction is trained to match the driver frame. “

Website: https://samsunglabs.github.io/MegaPortraits/

 

 

 

Chat with Einstein the digital human

May 18, 2021 /

Lately I have taken a massive interest into Digital Humans and all they can offer using AI, machine learning and buckets of data.
This example is spot on using a figure that the world know so well and bringing him back to life for classrooms to ask him questions on all of his amazing work and his life. He responds in a casual way that doesn’t feel too forced enabling you to actually start a conversation, i would recommend using your mic vs typing to give the conversations a natural feel.

Overall I was very impressed when i have my little chat with one of my heros.

Audio content production company Aflorithmic and digital humans company UneeQ teamed up to create a digital version of the famous genius, Albert Einstein. – See the video below and to chat to him click this LINK

Source: Interesting Engineering

Insane Motion with Driving Sim

May 18, 2021 /

Mean Gene Hacks has created a motion device that connected with his driving sim gives him real time motion feedback, he does this with a devise that manipulates your nerves making you move is if you were in a real car turning a corner, or in the case of the example in the video, falling off your chair when you crash the car.
The cost to make this motion sim was 50 dollars – he made a video on how here

It turns out a process called galvanic vestibular stimulation—also known as GVS—can be used to alter a human’s sense of balance by electrically stimulating a nerve in the ear using electrodes.

Indy Autonomous Car Race

January 19, 2021 /

Yes, its real!
A race happening this year.

Who?
A competition among accredited, tax-exempt colleges and universities (including foreign institutions of higher education that are organized and operated in a manner consistent with requirements for exemption from federal income tax under the laws of the United States) to create software that enables automated-capable racecars to best compete and aspire to finish first in a head-to-head race on the Indianapolis Motor Speedway’s (IMS) famed oval.

Prize?
1 Million dollars to the first team to cross the finish line in 25 minutes or less in a head-to-head, 20-lap race of automated Dallara IL-15 racecars around the Indianapolis Motor Speedway oval

Here is the CES press conference

and Here is the competition website

Five AI developments will shape 2021 and beyond

January 19, 2021 /

1. AI and vaccine development
It typically takes years, if not decades, to develop a new vaccine. But by March 2020, vaccine candidates to fight covid-19 were already undergoing human tests, just three months after the first reported cases.

2. Fully automated driving and the rollout of robotaxis
Autonomous driving technology continued to mature in 2020, with the industry’s leading companies testing driverless cars and opening up robotaxi services to the public in various cities.

3. Applied natural language processing
In 2020, natural language systems became significantly more advanced at processing aspects of human language like sentiment and intent, generating language that aligns with human speaking and writing patterns, and even visual understanding, meaning the capability to express understanding about an image through language.

4. Quantum computing
Quantum computing has the potential to supercharge AI applications compared to binary-based classical computers

5. AI chips
Chips can already cope with a small amount of AI processing, but with the need for more AI we will need to develop chips that can focus on the deep learning processing required.

Read the full article on MIT

Google FREE AI assisted monster maker

January 11, 2021 /

This is one of those tools you will spend hours on without getting the result you really wanted.

Google has launched a fun tool that takes your strange sketches and turns them into a kind of 3D monster.

Its fun and I am sure lots of AI and tech behind the scenes, but not something to use in the real world where monster don’t exist, well not looking like these ones.

Check it out if you have a spare 10 mins at chimera

The Future of clothes shopping?!

December 17, 2020 /

Zozo have made a second version I assume of their try it on suit, I base this on the fact its called ZozoSuit2.
The suit takes all your measurements along with your mobile device to make sure you don’t have any ill fitting clothes in the future when ordering online.
In a covid world this is genius, while looking into the suit i saw they also do a mat for shoes.

References:
Matt
Suit

Create 3D worlds via speech

November 24, 2020 /

Create 3D worlds using half a million different 3D objects.
you can create with and without code and also by recognition speech.

Once your world is created you can view on a number of platforms including VR headsets.

The concept seems great, the telling will be in how the interaction with the worlds works and how easy is it to
manipulate the objects to move and interact with each other.

Product site here {Anything World}

Need help learning a new language?

August 27, 2020 /

 

Vagus nerve stimulation has been used for more than 20 years to treat conditions like epilepsy, but it usually involves surgery to implant electrodes so they are directly in contact with the nerve in the neck

Now some smart folk at the university of California and San Francisco have developed an ear bud that connects directly to your brain and helps people learn unfamiliar sounds new languages. 

The device has been tested on 36 English speaking volunteers, the device is so advanced you are not aware its actually working. out of the 36 test it seems to have worked on 2/3 of the test group.

Read more on the

NewScientist

for the full article

Continue reading

Lancôme’s VR Pop-up Store

August 24, 2020 /

Lancôme has opened a pop-up VR store to reinvent the Future of Beauty retail Post Covid according to Forbes 

We have seen a few of these VR stores pop-up (no pun intended) recently, if kind of makes me chuckle inside a little as we were presenting these type of ideas way back in 2005 and no one was interested, maybe it was to early for this type of engagement via online. What this does is gives me hope that the online experience can be as entertaining and engaging as it once was when Flash was alive.

Reference Link

Robot Can Guess How You’re Feeling by the Way You Walk

August 4, 2020 /

Yes you read correctly, Researchers at the University of Maryland have developed an algorithm called ProxEmo

This new discovery will enable robots to interact with humans based on their gathered data while the person is walking towards them, If angry the robot will take a wider route around the person, if sad they could approach them and ask if they would like assistance. 

 

More information on this new innovation can be found on wired

 

The New York Times R&D

July 29, 2020 /

Screen recording by Azad Balanian

The New York Times has a R&D site, thats the first piece of big news, the second is this web based experience called photogrammetry where scrolling lets you enter into an immersive the story inside the visual
Imagine being able to do this with all flat images, giving you the ability to explore and immerse into different world through a visual portal. 

What is Flutter

July 16, 2020 /

Flutter is a development tool kit to develop apps, mobile web and deskop from a single codebase.. meaning you can create apps for Apple and Android phones with a single codebase.. Wow.

Direct quote from their website 

“Flutter is Google’s UI toolkit for building beautiful, natively compiled applications for mobile, web, and desktop from a single codebase.”

I have yet to try this, but its defiantly on my to do list, this would make app development so much simpler and faster if all they say is true.

Here is a video that shows what its all about.

Some great examples of Flutter Apps can be found here with the developer stories.