Question about keeping viewpoint angles of input sketches

[YokkaBear]

Thank you for your impressive work and generous sharing.

I have made it to generate some 2D images from the human sketches of my dataset with your code and pretrained models. However, I noticed that the generated 2D images all seem to be drawn from the front (canonical) view, while the viewpoint information, i.e. different observation angles, of the input skethes seem to be lost.

So I wonder if your model could keep the viewpoint information of the input sketches, and if it is possible how could I modify the code to keep the viewpoint information in the output 2D images. Thank you a lot.

[3shry]

hi YokkaBear am trying to train the model from scratch so if know how to do this can you help me ? and also how did you put your own data set in the code ? thanks in advance.

[YokkaBear]

@3shry Sorry, I didn't write the training code of this model. What I did is just using the pre-trained models provided by the author to generate realistic images from the sketch dataset of my own.

[3shry]

ok thanks :)