Computer Graphics  

In the the first part of a real-time rendered short film “Adam”, the developers of the Unity engine have broken new ground in realistic 3D graphics. Adam illustrates the high quality systems that are coming available to gaming, VR and other applications. 

"Adam" (video below) relates the tale of a humanoid robot coming to life in a dark vessel, and then being released out into the wild with hundreds of others like him. The robot's breathing indicates that there may be more to the story. Is Adam robotic consciousness, or an uploaded human being?

Related articles

• NAO Robot Helps Children With Autism 
• Andrew McAfee Asks - What Will Future Jobs Look Like? 
• Robot Revolution - Will Machines Surpass Humans? 

The production of this sci-fi short was used to stress test the beta versions of Unity 5.4 and the cinematic sequencer currently in development. The team also used an experimental implementation of real time area lights.

"Adam" makes extensive use of the high fidelity physics simulation tool CaronteFX.

The Demo team also created some custom tools on top of the Unity engine to cover specific production needs. For this project they needed volumetric fog, transparency shader, and motion blur – to name a few. These tools are expected to be released soon as well.

The full length movie will be shown at Unite Europe 2016 in Amsterdam. We look forward to it!

SOURCE  Unity

By 33rd Square

Embed

 Computer Graphics  

A newly developed technology that uses an inexpensive facial mapping method can recreate and replace faces of celebrities, but the technology may also have applications in creating digital avatars and mindclones.

Soon, nearly everyone with a computer will be able to create inexpensive, controllable computer models of famous people’s faces in 3D just using online photos of celebrities, or anyone.

"This capability opens up the ability to create puppets for any photo collection of a person, without requiring them to be scanned," write the researchers from the University of Washington.

The researchers also were able to recreate idiosyncrasies, like facial ticks, of the celebrities they modeled, including Kevin Spacey and Daniel Craig. This work could let us interact with digital avatars that look and act like people we know.

Related articles Researchers Rewire Paralyzed Monkey To Control Arm Directly From The Brain Infographic - Are We Living In A Computer Simulation? Is Brown Fat The Key To A Healthier You?

Typically, creating CGI models of a human face is expensive and requires laser scanning and motion capture technology. The researchers postulated that for celebrities, there are more than enough paparazzi photographs online to capture digitally what they look like from just about every possible angle.

"The idea was to create realistic virtual models of people just from photos rather than complex lab set-ups," says researcher Ira Kemelmacher-Shlizerman. Led by Supasorn Suwajanakorn, the team collected around 200 photos each of various famous people from Google Images, taken in different poses and at varying angles.

"Don't underestimate how much people want to be someone else."

The photos were analysed using face-tracking software, and a realistic 3D model for their face and head created. Further analysis added wrinkles and textures that appear and disappear as expressions change.

"The result is a full 3D model you can turn right around," says Suwajanakorn.

As well as being able to manipulate the digital puppets any way they wanted, the team found they could realistically switch an actor's face with that of another – allowing them to be replaced throughout an entire TV show or movie, for example.

A real potential commercial application could be to provide famous animated faces for visual versions of Siri-like assistants, says Suwajanakorn. Another might be to automatically create 3D faces for telepresence robots, says Nicole Carey at humanoid robot maker Engineered Arts in Penryn, UK. "Don't underestimate how much people want to be someone else," she says.

The face of someone who has died could be recreated and driven with one of the emerging breed of chatbots trained – using the deceased's tweets and emails – to converse like them.

The system may also be useful for creating mindclones. "Our model could bring back your memories of the people you care about," says Suwajanakorn.




SOURCE  New Scientist

By 33rd Square

Embed

 Uncanny Valley  

It is hard to believe that the orangutan, "Maya," in a new commercial for the Scottish electrical utility is a real, well trained animal actor—she's not, she's 100% computer generated.

When you see the advertisement above, you will wonder how they trained an orangutan, "Maya," to perform the way she does.  As it turns out, they didn't trained it at all. It was entirely made with CGI by production house, The Mill.

"It has been an amazing ten month journey," says The Mill's Chief Creative Officer, Pat Joseph. "I've yet to have anyone tell me that that's not a real orangutan."

"I've yet to have anyone tell me that that's not a real orangutan."

Related articles Hard To Believe This Face Is Computer Generated  The Urban Uncanny Valley Fades Away Digital Avatars Crossing the Uncanny Valley

In the commercial, the majestic orangutan makes her way from the rainforest of Sumatra into our urban world.

To our eye, "Maya," totally crosses the uncanny valley.

The Mill created the photo-real 100% CGI Orangutan for leading energy supplier SSE. More details on the making of "Maya," are in the video below.

By 33rd Square

Embed

 Uncanny Valley  

Computer graphics artist Chris Jones has created one very realistic looking head using the latest software.  His short video of the piece called 'Ed' must be seen.

Australian-based computer game artist Chris Jones has created one of the most realistic human head simulations we've seen.

One person commented on Sploid, "This IS the most realistic human face I've ever seen produced via computer; however it's so perfect that something still screams uncanny valley."

The head, 'Ed,' was made with Lightwave, Sculptris and Krita, and composited with Davinci Resolve Lite. Jones also created the music for the video.  It has been an ongoing work for the artist.

Related articles Uncanny Valley Getting Closer With Cell-Level Simulated Skin  Digital Avatars Crossing The Uncanny Valley  Verbal IQ of a Four-Year Old Achieved in AI System

Jones has worked as a freelance children’s book illustrator, and following graduation with and industrial design degree, continued illustrating and animating before becoming a computer game artist at Beam Software (later to become Infogrames).

He left Infogrames in May 2000 to work full-time on a film called, The Passenger.

Soon this quality of avatar will be walking around in Second Life.



SOURCE  Chris Jones

By 33rd Square

Embed

 Special Effects  

To achieve the mass crowd effects in the movie World War Z, the film makers turned to a form of artificial intelligence. Visual effects firm Motion Picture Company picked up on an idea that WETA used for the Lord of the Rings movies - to make each zombie an individual actor with goals and behaviors.

For the Brad Pitt film World War Z, London-based VFX house Moving Picture Company had to make enormous zombie hoards behave with a bit of intelligence.

World War Z is an apocalyptic horror film directed by Marc Forster. The screenplay is loosely based on the 2006 novel of the same name by Max Brooks.

Related articles David Hanson Wants To Create Genius Machines  Short Film Written By AI Is Rather Funny  How AI is Changing the Way We View Intelligence, the World, and Ourselves

Animating the sequences by hand would not have allowed the thousands of zombie 'actors' to be in the shots, so the company turned to artificial intelligence.  Using digital creatures, whose movements came from motion-capture performances of real people running up nets and falling down ramps, the team programmed a kind of artificial intelligence, a proprietary crowd-simulation program called Alice.

This type of crowd animation intelligence was pioneered in the Lord of the Rings movies by WETA Digital's Massive software. Through the use of fuzzy logic, the software enables every agent to respond individually to its surroundings, including other agents.

These reactions affect the agent's behavior, changing how they act by controlling pre-recorded animation clips, for example by blending between such clips, to create characters that move, act, and react realistically.

For the movie’s massive piles of Zs in Jerusalem, the VFX company—one of a handful that worked on World War Z—had to build zombie “agents” that could “act” on their own. The
“All complex crowd shots got layers of hand-animated zombies,” said MPC senior CG supervisor Max Wood. “We’d start off setting the shots up in Alice, our in-house crowd tool, then we’d work out where we wanted to add the additional animation detail.”

How long before such crowd software makes it's way into video games and virtual worlds?

SOURCE  Wired

By 33rd Square

Subscribe to 33rd Square

 Digital Avatars  

Researchers using photographed samples of skin from people's chins, cheeks and foreheads at a resolution of about 10 micrometers, have created super-realistic simulated CGI skin with detail such that each skin cell spreads across only three pixels.

New research could further CGI graphics with simulated skin that is faithful down to the level of individual cells.

Creating realistic faces is one of the biggest challenges for CGI, in large part because skin's appearance is the sum of a complex interplay of tiny features and flaws. Get any of those factors wrong, and the CGI face comes out looking eerily wrong. "The renderings can only be as real as the input data," says Abhijeet Ghosh at Imperial College London. "And that's where we come in."

Related articles Simulating Roundworms May Help Us Understand of the Basic Principles of the Brain  Computer Scientists Find That Evolution May Not Require Outside Factors  Digital Avatars Crossing The Uncanny Valley

Ghosh and Paul Debevec of the University of Southern California (USC) and their colleagues had already developed a way to simulate light reflecting off human skin. It involves splitting the light into four rays: one that bounces off the epidermis and three that penetrate the skin to varying depths, scattering before being reflected.

The team have now massively cranked up the level of detail. Using a specially developed lighting system and camera, they photographed samples of skin from people's chins, cheeks and foreheads at a resolution of about 10 micrometres, so that each skin cell was spread across roughly three pixels. They then used the images to create a 3D model of skin and applied their light reflection technique to it. The result was CGI skin complete with minute structures like pores and microscopic wrinkles. Finally, they fed the CGI images to an algorithm that extended them to fill in an entire CGI face.

Usually, CGI uses a standard set of values for skin structure, says Ghosh. But for big-budget films, digital effects companies like Weta Digital – which used some of Ghosh and Debevec's techniques in the movie Avatar, for example – prefer to tailor skin textures to individuals. To create the blue-skinned Na'vi, for example, artists took surface details like moles and wrinkles and added them to the characters by hand. "In movies they zoom in to show that stuff off," says Ghosh, but the work is a slow process. Ghosh and Debevec's system, which Ghosh presented at the Games and Media Event at Imperial College London in May, could automate this level of customization.

It's not only the entertainment industry that is eyeing this technology. In 2010, the cosmetics company Avon gave Ghosh funding to explore whether his digital skin could be used to simulate the application of different kinds of make-up. Other cosmetics firms have also showed interest in the idea. Ghosh thinks that one day we will have an app that offers a virtual try-before-you-buy service for make-up. "You would arrive at a kiosk and have your face scanned," he says. The software would then show you exactly what your skin would look like with, for example, a certain foundation applied, he says.

Next, he team at USC is working with games publisher Activision to try to find a way to bring these sort of high quality faces to games as soon as possible.


SOURCE  New Scientist

By 33rd Square

Subscribe to 33rd Square