3D face: fast, accurate and stable reconstruction

dracoshield wrote: post #3

cleardusk wrote: post #2

Welcome to give it a try :)

could you please share the training code so that I could better understand the implementation?

thanks for your interest, releasing the training code should be granted by my lab leader. I am trying to apply for it. If you have any question, welcome to raise an issue or email me :)

Re: 3D face: fast, accurate and stable reconstruction

#5

Post by abetusk » Mon, Aug 31, 2020, 6:08 PM UTC

cleardusk wrote: post #2

Welcome to give it a try :)

I had some problems getting it to run but after some handholding I managed to get all the demos to run. Amazing stuff!

I'll try to open an issue with all the problems I encountered.

I would also appreciate a demo with data output as well (actual 2d/3d points) along with a short description of what the format is.

Can this be used real-time?

Re: 3D face: fast, accurate and stable reconstruction

#6

Post by cleardusk » Mon, Aug 31, 2020, 6:22 PM UTC

abetusk wrote: post #5

cleardusk wrote: post #2

Welcome to give it a try :)

I had some problems getting it to run but after some handholding I managed to get all the demos to run. Amazing stuff! I'll try to open an issue with all the problems I encountered. I would also appreciate a demo with data output as well (actual 2d/3d points) along with a short description of what the format is. Can this be used real-time?

Thanks for your interest and try. The theory computation complexity is described in the paper, it is rather small. However, whether achieving real-time really depends on your hardware, your need and the code optimization.

Re: 3D face: fast, accurate and stable reconstruction

#7

Post by fxtentacle » Mon, Aug 31, 2020, 6:48 PM UTC

Wow, that's very impressive performance. Thanks for sharing :)

Re: 3D face: fast, accurate and stable reconstruction

#8

Post by yboris » Mon, Aug 31, 2020, 7:38 PM UTC

I love that the Colab notebook runs flawlessly!

I humbly recommend you add code so people can try out with online images:

  from skimage import io

  def get_image_from_url(url):
    # download the image using scikit-image
    print("downloading", url)
    image = io.imread(url)
    return image

Re: 3D face: fast, accurate and stable reconstruction

#9

Post by rhacker » Mon, Aug 31, 2020, 10:24 PM UTC

The cost of motion capture for video games, movies and deep fakes just dropped significantly.

Re: 3D face: fast, accurate and stable reconstruction

#10

Post by cleardusk » Tue, Sep 01, 2020, 1:03 AM UTC

yboris wrote: post #8

I love that the Colab notebook runs flawlessly! I humbly recommend you add code so people can try out with online images: from skimage import io def get_image_from_url(url): # download the image using scikit-image print("downloading", url) image = io.imread(url) return image

Thanks for your advice : )