search

HackGT / photo-style

A hackathon themed photobooth using neural style transfer
2 stars 1 forks source link

Investigate other style transfer models #9

Open joel99 opened 5 years ago

joel99 commented 5 years ago

Mainly https://github.com/xunhuang1995/AdaIN-style. Segmentation in photobooth remains the same, but for an artistic endeavor the possibilities in photobooth should be expanded for more sophisticated techniques.

ruyimarone commented 5 years ago

Something I didn't investigate that much is the input and training style size. If I recall correctly, the current model gives different results depending on the resolution of style image used for training. It would be nice to tune this to whatever size input image we use. Also I think the input image size was hardcoded based on a scaling of the default resolution of the camera we were using.