Skip to content

Aim: Create a facial template for virtual/simulated characters through morphing faces of fashion models. I utilized Implementation of the paper Image2StyleGAN.

Notifications You must be signed in to change notification settings

bshim181/StyleGan-MorphTwoImages

Repository files navigation

Image2StyleGan

I have used images of fashion models, preprocessed facial part locations, then worked to morph two faces to create a facial template for potential virtual/simulated characters.

Acknowledgement & References

Took zaidbhat1234/Image2StyleGAN implementation of the paper "Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?"

Results

Screen Shot 2022-08-23 at 9 07 14 PM

Room for improvements

  • Denoise the background.
  • Facial distortions when facial parts are covered.

Screen Shot 2022-08-23 at 9 14 01 PM

Directions

  • Utilize the segmentation model to filter out the irrelevant background noises.
  • Educate the model to reconstruct facial parts in the style of the target image based on their positional and conceptual information.
  • Incoporate the concept of "beauty standard" into the encoder. Aim to morph two images in a manner that complements one another.

About

Aim: Create a facial template for virtual/simulated characters through morphing faces of fashion models. I utilized Implementation of the paper Image2StyleGAN.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages