about the usecase of the project. about spade HOT 6 OPEN

+1

from spade.

COCO-stuff does contain human label, but it is actually a very hard problem to generate realistic human on datasets of human in various poses. The generated human images on COCO-stuff look pretty bad.
The current best GAN models can only generate realistic human when all the keypoints / part segmentations are given , or when the human images are aligned. I think our model can be used to generate realistic human images if it is trained with part segmentation, but there is no pretrained model that does that.

from spade.

I've tried pix2pixHD(label and image) and other GAN to generate fake humans, the result is weird, most of them looks like just a mess of meats. Now I'm using stylegan (https://github.com/NVlabs/stylegan), maybe
it's the light of the tunnel, but it's take a lot of time for training (2x1080ti, 10K images, 10 day's passed, and it still wade on and on, and on).

from spade.

@banyet1 can you post some of the example images which were generated using pix2pixHD?

from spade.

@naren142 here are a few I made w/ Pix2PixHD:
http://www.mattkenney.me/fake-news-with-openpose-and-pix2pix/
http://www.mattkenney.me/openpose-pix2pix/

from spade.

If you use the CelebA-HQ Mask dataset.
SPADE can also generate fake humans.

Here is my tensorflow version result

from spade.