Super-detailed CGI human skin could finally cross the uncanny valley, bring realistic faces to games and movies

Computer technology has grown ever more advanced in recent decades, but we reached an impasse a while back where technology collided with biology in an unexpected way. Trying to create digital versions of human faces usually resulted in something bizarre or downright disturbing. The phenomenon, known as the uncanny valley, is still vexing for the movie and game industries. However, a team led by Abhijeet Ghosh and Paul Debevec of the University of Southern California (USC) has developed a method to make artificial faces even more real, perhaps crossing the uncanny valley. It turns out the answers were only skin-deep.

The human brain is precisely tuned to understand what a face is supposed to look like. These subtle cues are deeply ingrained and when we find them missing, the response is often viscerally negative. It can be as simple as muscles around the eyes contracting oddly, or the way lips part during speech. Science is getting closer to nailing down the mechanical processes, but the USC team is tackling the most challenging aspect — skin.

It turns out modeling the reflection of light on skin is extremely complicated because skin itself is extremely complicated. It’s a patchwork of bumps, pores, blemishes, and tiny wrinkles that creep in as you approach middle age. When these details are missing, digital skin doesn’t look real and we venture into uncanny valley territory no matter how accurate the movements are. The technique being developed at USC more accurately simulates skin in a few ways, the first has to do with the lighting.

Each simulated light source is split into four rays — one that bounces off the epidermis, and three others that penetrate the skin to different depths before being scattered. The result is a more natural sheen with realistic shadows.

To make this technology really work, the team also cranked up the level of detail for CGI skin. Using a special scanner, Ghosh and Debevec took extremely high resolution images of human skin from volunteers’ cheeks, chins, and foreheads. Each pixel in the images contained an area only 10 micrometers across (that’s 0.00001 meters, by the way). At this level of detail, a single skin cell is only three pixels wide on average.

The scans were used to generate incredibly detailed 3D renders of skin. When combined with the new simulated lighting, the results are incredibly impressive. The CGI network of pores and bumps make the faces look almost real as the artificial light plays across them.

There has been intense interest from game developers and Hollywood as this project has proceeded. The CGI blockbuster Avatar used a rudimentary version of the USC technology to make the film’s blue-skinned aliens more realistic. Activision and Nvidia have been collaborating with USC in hopes of developing a software package that can generate photorealistic faces on consumer hardware like game consoles and PCs. The day might be fast approaching that your in-game avatar looks completely real in every way that matters.

View the original article here

Super-detailed CGI human skin could finally cross the uncanny valley, bring realistic faces to games and movies

Computer technology has grown ever more advanced in recent decades, but we reached an impasse a while back where technology collided with biology in an unexpected way. Trying to create digital versions of human faces usually resulted in something bizarre or downright disturbing. The phenomenon, known as the uncanny valley, is still vexing for the movie and game industries. However, a team led by Abhijeet Ghosh and Paul Debevec of the University of Southern California (USC) has developed a method to make artificial faces even more real, perhaps crossing the uncanny valley. It turns out the answers were only skin-deep.

The human brain is precisely tuned to understand what a face is supposed to look like. These subtle cues are deeply ingrained and when we find them missing, the response is often viscerally negative. It can be as simple as muscles around the eyes contracting oddly, or the way lips part during speech. Science is getting closer to nailing down the mechanical processes, but the USC team is tackling the most challenging aspect — skin.

It turns out modeling the reflection of light on skin is extremely complicated because skin itself is extremely complicated. It’s a patchwork of bumps, pores, blemishes, and tiny wrinkles that creep in as you approach middle age. When these details are missing, digital skin doesn’t look real and we venture into uncanny valley territory no matter how accurate the movements are. The technique being developed at USC more accurately simulates skin in a few ways, the first has to do with the lighting.

Each simulated light source is split into four rays — one that bounces off the epidermis, and three others that penetrate the skin to different depths before being scattered. The result is a more natural sheen with realistic shadows.

To make this technology really work, the team also cranked up the level of detail for CGI skin. Using a special scanner, Ghosh and Debevec took extremely high resolution images of human skin from volunteers’ cheeks, chins, and foreheads. Each pixel in the images contained an area only 10 micrometers across (that’s 0.00001 meters, by the way). At this level of detail, a single skin cell is only three pixels wide on average.

The scans were used to generate incredibly detailed 3D renders of skin. When combined with the new simulated lighting, the results are incredibly impressive. The CGI network of pores and bumps make the faces look almost real as the artificial light plays across them.

There has been intense interest from game developers and Hollywood as this project has proceeded. The CGI blockbuster Avatar used a rudimentary version of the USC technology to make the film’s blue-skinned aliens more realistic. Activision and Nvidia have been collaborating with USC in hopes of developing a software package that can generate photorealistic faces on consumer hardware like game consoles and PCs. The day might be fast approaching that your in-game avatar looks completely real in every way that matters.

View the original article here

Corning Willow Glass used to make flexible solar power roofing shingles, could lower the cost of solar power significantly

The US government’s National Renewable Energy Laboratory has built flexible solar cells out of Corning’s Willow Glass. These new solar cells are strong enough that they could eventually replace roofing shingles, which would significantly shrink the biggest barrier to mass adoption of solar power: the cost of installation.

As you probably know, Corning is the manufacturer of Gorilla Glass, which furnishes the front of many smartphones, including the iPhone, and most HTC and Samsung devices. (See: Gorilla Glass coming to cars, making them more resilient and efficient.) Gorilla Glass is essentially a variety of alkali-aluminosilicate toughened glass that has been engineered for a combination of desirable factors (high strength and toughness, while remaining thin and light).

Willow Glass, on the other hand, is a flexible, transparent, thin (0.1mm) borosilicate glass that’s intended to be used as a substrate — a material on which other components, such as LCD or OLED electronics, can be laid down. Being a borosilicate glass, Willow Glass – just like Pyrex, which was developed by Corning in 1915 – is very heat resistant, which is useful when the creation of modern displays can involve temperatures measured in hundreds of degrees Celsius. Most importantly, though, Willow Glass is flexible enough to be rolled up and used in continuous roll-to-roll processes. It is this last point that is most exciting to display manufacturers, as it could significantly speed up production and reduce costs.

Willow Glass’s flexibility may lead to bendy or wraparound displays, but it’s important to note that you still need another layer to protect the Willow Glass (Corning recommends Gorilla Glass, of course). At just 100 micrometers thick, Willow Glass is flexible, but it isn’t strong like Gorilla Glass. If you’re waiting for a bendy device, devices that use plastic displays, such as LG’s plastic e-ink display, are probably a better bet. Willow Glass’s combination of flexibility, transparency, and heat resistance does make it a very good option for the creation of cadmium telluride solar cells, however.

Cadmium telluride photovoltaic cells are the only thin-film photovoltaic technology that’s cheaper than crystalline silicon — but until now, there hasn’t been a transparent substrate that also has the thermal resistance to withstand manufacturing. The DoE’s National Renewable Energy Laboratory (NREL) is reporting that it has built cadmium telluride (CdTe) solar cells on Corning’s Willow Glass (pictured right). For now, these are very small cells, but they could be used as roofing shingles. If production of these cells can be scaled up roll-to-roll processing, it would be possible to create very cheap solar power shingles that could be used instead of conventional asphalt, brick, or slate shingles.

When it comes to adopting solar power, the cost of installation is one of the most prohibitive factors. While solar panels themselves generally cost less than $1 per watt, the cost of installation can be five or 10 times that amount. Instead of paying a huge amount to have solar panels installed on your roof, it would be much cheaper if new houses were simply built with roofing made of solar panels. It would be rather exciting if each home produced the electricity that it required — in sunny climes, at any rate. (See: NASA’s cold fusion tech could put a nuclear reactor in every home, car, and plane.)

View the original article here