Jason MacAllister’s Morph Extravaganza

For Computational Photography, 15-463 (Project 2)

Carnegie Mellon University                                  jmm59@pitt.edu

 

Photos and point sets that were used for my experiments can be found aqui.

The 61 frames generated for class morph can be found here.

 

The first part of this assignment was to generate 61 frames of a morph between myself and another student.  This turned out a little lika thisa:

Sorry about the borders, these were generated in the “learning phase” (I still had no idea what I was doing).  These frames were all approximately 300x300 pixels, allowing a generation time of about 30 seconds per frame.  The rest of my images are usually 768x1024, and they took about 10-15 minutes each (ouch!).

 

 

Mean (as in average) Face

 

Here’s the average face of my class:

Our teacher referred to this as the “average CMU undergrad.”

 

Here’s the average face generated from 18 total donors (basically my class plus a large amount of my family):

 

Here’s just the males (10 faces):                             And the females (7 faces):

 

This is my face morphed to the average geometry:            And this is the average face in the shape of mine:

         

 

 

Family Study

Next I looked at similarities within families.

Here’s my family:

Aren’t they the sweetest?

 

Now, let’s play.  Here’s the average:

Nothing like face averaging to bring out the similarities in a family.

 

Here’s the men (me and my dad):

Apparently I’m going to look exactly like my dad when I get old- I mean older…  It appears that I have no distinguishing features, and the average just looks like a younger version of Pa.

 

Here’s the women:

 

And here’s the average of my mom and dad.  By far the most disturbing, it really doesn’t indicate what their children look like as much as I had expected.  Mostly just looks like a bearded mommy.  It does bring out the similarities in my parents’ faces, however, as several people have pointed out.

 

Next I averaged the faces of my wife and myself, in the hopes of determining what our children will look like.

Remember that picture of Amanda?  Well, here’s our offspring:

Maybe we should rethink that whole children thing.  Looks like a possessed adolescent boy wearing suspenders.

 

Maybe a combination of the wife and, say, the family dog would be more appealing:

 

Or perhaps me and my iguana:

 

Oh heck.  Let’s try the two pets together:

THAT is crazily awesome.  I had to remove the background (as in with the Amanda-dog) cuz it was too confusing.

 

Enough torturing the MacAllisters.  Let’s see how the in-laws fare!

Here’s the rest of Amanda’s family:

(this is the best picture I could find of Zack, just ignore the other two, so I’m only pulling his face from it)

 

So here’s the family average:

They don’t seem to mesh as well, especially since some have their mouths open and some don’t.  Also, we get that weird collage effect around the borders because of the differences in picture context.  But you gotta love that bow tie!

 

Let’s look at just the men:

Apart from the strange spirits floating around the head, this turned out to be a pretty good combination.  Those dang lips though.

 

Here’s the women:

 

Finally, here’s the average male and female face from both families combined:

 

And the average of those two:

 

Caricatures

 

Here’s me with the deviation of my face from the average amplified (distinguishing features become more pronounced):

…and I hate it.  If you think about it, this is kinda the opposite of what I just did above (morphing my face to the average geometry).  Now I’m morphing my face away from the average geometry.  So it makes sense that my face is now skinnier, as opposed to fatter in the previous image.  This image is exaggerated by one full magnitude of deviation.

 

Here’s the same caricature concept, only implemented with skin texture/color instead of geometry. 

At first glance it seems like it’s only higher contrast or brighter, but it’s actually only the parts that are different from the average face that are brighter.  The redness of my lips seem to be emphasized a lot, as well as my green t-shirt, and any blemishes in the skin (because Mr. Average is OH SO PURE.)

 

Here’s my wife, Amanda:

 

And here’s her caricature (geometry and texture):

As disturbing as it is, I’m kinda impressed that it works.  She’s smiling a little more than the average, so now she has a huge grin.  And it really emphasized the narrowing of her head width from top to bottom.

 

Also, here’s the texture deviation from that caricature.  This is what’s added on top of the regular image to emphasize differences.

You can see the shine spots that were brought out, as well as the brightness in her eyes.

 

Here’s some other caricatures of people you’ll recognize:

 

Appendix A

Other combinations:

+=

 

Appendix B

Here’s some random junk that’s left over but definitely worth showing: