yego.me
💡 Stop wasting time. Read Youtube instead of watch. Download Chrome Extension

Animating a photo-real digital face - Paul Debevec


5m read
·Nov 8, 2024

One of the biggest challenges in computer graphics has been able to create a photoreal digital human face. One of the reasons that's so difficult is that, unlike aliens and dinosaurs, we look at human faces every day. They're very important to how we communicate with each other, and as a result, we're tuned into the subtlest things that could possibly be wrong with the computer rendering in order to believe whether these things are realistic.

What I'm going to do in the next five minutes is take you through a process where we tried to create a reasonably photorealistic computer-generated face using some computer graphics technology we've developed, and also some collaborators at a company called Image Metrics. We're going to try to do a photoreal face of an actress named Emily O'Brien, who's right there, and that's actually a completely computer-generated rendering of her face. By the end of the talk, we're going to see it move.

The way that we did this is we tried to start with Emily herself, who was gracious enough to come to our laboratory in Marina del Rey and sit for a session in Light Stage Five. This is a face scanning sphere with 156 white LEDs all around that allow us to photograph her in a series of very controlled illumination conditions. The lighting that we use these days looks something like this. We shoot all of these photographs in about three seconds, and we basically capture enough information with video projector patterns that drape over the contours of her face in different principal directions of light from the light stage to figure out both the coarse scale and the fine scale detail of her face.

If we zoom in on this photograph right here, you can see it’s a really nice photograph to have of her because she's lit from absolutely everywhere at the same time to get a nice image of her facial texture. In addition, we've actually used polarizers on all the lights. Just like polarized sunglasses can block the glare off of the road, polarizers can block the shine off of the skin, so we don't get all those specular reflections to take this map.

Now, if we turn the polarizers around just a little bit, we can actually bring that specular reflection of the skin back in, and you can see she looks kind of shiny and oily at this point. If you take the difference between these two images here, you can get an image lit from the entire sphere of light of just the shine off of Emily's skin. I don't think any photograph like this had ever been taken before. We've done this, and this is very important light to capture because this is the light that reflects off of the first surface. The skin doesn't get underneath the translucent layers of the skin and blur out, and as a result, it's a very good cue to the detailed shape of the skin pore structure and all the fine wrinkles that all of us have—the things that actually make us look like real humans.

If we use information that comes off of the specular reflection, we can go from a traditional face scan that might have the gross contours of the face and the basic shape, and augment it with information that puts in all of that skin pore structure and fine wrinkles. Even more importantly, since this is a photometric process that only takes three seconds to capture, we can shoot Emily in just part of an afternoon in many different facial poses and different facial expressions.

So, here you can see her moving her eyes around, moving her mouth around, and these were actually going to use to create a photoreal digital character. If you take a look at these scans that we have of Emily, you can see that the human face does an enormous amount of amazing things as it goes into different facial expressions. You can see things—not only does the base shape change, but all sorts of different skin buckling and skin wrinkling occurs. You can see that the skin pore structure changes enormously from stretched skin pores to the regular skin texture.

You can see the furrows in the brow and how the microstructure changes there. You can see muscles pulling down the flesh to bring our eyebrows down, and our muscles bulging in her forehead when she winces like that. In addition to this kind of high-resolution geometry, since it's all captured with cameras, we get a great texture map to use for the face. By looking at how the different color channels of the illumination—the red, green, and blue—diffused the light differently, we can come up with a way of conveying the skin in the computer that, instead of looking like a plaster mannequin, actually looks like it's made out of living human flesh.

This is what we used to give to the company Image Metrics to create a rigged digital version of Emily. We're just seeing the coarse scale geometry here, but they basically created a digital puppet of her where you can pull on these various strings, and it actually moves her face in ways that are completely consistent with the scans that we took. In addition to the coarse scale geometry, they also used all of that detail to create a set of what are called displacement maps that animate as well. These are the displacement maps here, and you can see those different wrinkles actually show up as she animates.

So, the next process was then to animate her. We actually used one of her own performances to provide the source data. By analyzing this video with computer vision techniques, they were able to drive the facial rig with the computer-generated performance. So what you're going to see now, after this, is a completely photoreal digital face. We can turn the volume up a little bit if that's available.

Image Metrics is a marvelous performance-driven animation company. We specialize in high-quality facial animation for video games and films. So, if we break that down into layers, here's that diffuse component we saw in the first slide; here's the specular component animating—you can see all the wrinkles happening there—and there's the underlying wireframe mesh. And that's Emily herself.

Now, where are we going with this? Here, we've actually gone and gone a little bit beyond Light Stage Five. This is Light Stage Six, and we're looking at taking this technology and applying it to whole human bodies. This is Bruce Lom, one of our researchers in the group, who graciously agreed to get captured running in the light stage. Let's take a look at a computer-generated version of Bruce running in a new environment. Thank you very much.

More Articles

View All
Witness to Steve Irwin's Death - Smarter Every Day116
Hey it’s me Destin, welcome back to Smarter Every Day. So I think we will all agree that Steve Irwin was one of the best science communicators that has ever existed. I mean he knew the knowledge and it was like a fire in his bones; he had to share it wit…
What If Everyone JUMPED At Once?
Hey, Vsauce. Michael here. And what if every single person on Earth jumped at the exact same time? Could it cause an earthquake or would we not even be able to tell? Well, first things first, let’s talk about the Earth’s rotation. The Earth spins, that’s …
Alienated | Vocabulary | Khan Academy
Hey wordsmiths! Just checking in; you doing okay? The word we’re talking about today is “alienated.” “Alienated” it’s an adjective and it means feeling excluded and apart from other people. Kind of a bummer word, but at the same time, a fascinating one. …
Why are snowflakes like this?
[Ken] Now, I’m gonna turn on 2000 volts. [Derek] What? And this is the first step in creating snowflakes in the lab. This is totally wild. What? Crazy, huh? The tips of those needles are like a hundred nanometers in diameter. [Derek] That is so wild.…
Daily Eccentric Habits of Kevin O’Leary
[Music] Everybody asking all the time, how do you keep everything moving forward when you’re traveling all over the place? This is a good example. I’m out in California here at the Sony lot, shooting season 11 of Shark Tank. Now, this is pretty industrio…
2015 AP Calculus AB/BC 1c | AP Calculus AB solved exams | AP Calculus AB | Khan Academy
All right, part C. At what time ( t ) where ( 0 \leq t \leq 8 ) is the amount of water in the pipe at a minimum? Justify your answer. All right, well, let’s define a function ( w ) that represents the amount of water in the pipe at any time ( t ), and th…