Hacker News Reader

Comment by draz | Hacker News Reader

Anyone from DreamWorks (or any other studio)? Could this be used to generate crowds of people in movies, or is it too inefficient?

View on HN

It would be way more efficient to build a face with parameterized measurements (much like character-builders used in video games) and then randomly jitter the parameters.

I have been looking for a piece of open source code that would accept some facial parameters and generate a 2D or 3D rendering of a face or a head.

The degree of flexibility found in, for example, Second Life would be awesome.

Any leads?

This paper is relevant: http://www.cs.cmu.edu/~efros/courses/AP06/Papers/Blanz-siggr...

Of course, you need their database to make the algorithm work, but if you emailed the authors they might be accomodating..

I remember hearing in the commentary for The Incredibles that they basically used one basic face model as the basis for everything. I imagine they did this to avoid having to rig individual models for animation every time they made a new one, plus they could do random faces for the minor characters.

Sounds like a very convoluted way of generating random faces.

Only if DreamWorks intends to start making cubist movies, I think.

It could just be used to randomly pre render the faces. Efficiency won't be as big of an issue when you're prerendering.

Efficiency is an issue. You can generate thousands of faces using an algorithm meant for that in a few seconds and this would take lots of computer time to generate just one decent one. Even if pre-rendering you're still paying for all the computer time.

Reply on news.ycombinator.com