Another thing that's crappy is the FPT3CM model can move the eyes of the jpeg texture plastered on top of it, but It really struggles to do so.
This gives the end result on the final swap of a secret mouth coming out of the normal mouth. (generic teeth may sound ok, but you'd be shocked how much of an identifying feature someone's teeth are) And even then, it can sometimes suck at properly "marking" the "mouth edges" of the lips. The very first mistake you probably noticed is that it does not have real mouth. Why these face-pictures-turned-into-3D-modeled-videos are bad.Īs you watch that quad video of Brad Pitt's face moving around, I'm sure you noticed where it goes bad. If your curious what this looked like, these are the videos I made from the 4 photos, which I used my B-data. Basically the way it works is I was able to to plaster all 4 of these faces onto a 3D Human skull template, which I could control the rough 3D shape of, like they were a texture file on a 3D model in a video game. By using a Face-Picture-to-3D-Controllable-Model application (I don't know what to call this, lets just call it FPT3CM app from now on). In fact I made 1000's of images from those original 4 photos. that title is a little bit clickbait, because although I started with only 4 images for my B dataset, I created more images/data from those 4 photos I started with. Pretty decent right? I mean, it's not going to fool anyone, but for just 4 source pics, its pretty good right?Ĭonfession time. This video is not in HD because I couldn't be bothered lol Make sure HD is on (but don't maximize video)Īnd here is a direct comparison between the original video vs the swapped version. Here are the 4 images I used,Īnd here are the final results. Surly that title has to be clickbait right? I mean, You need to have 1000's of images of your B data all different angles and facial movements for the model to be able to learn how to smoothly move a face, right? Well.
0 kommentar(er)
