about the comparison experiments

[gouchaonijiao]

Hello! I am curious about the details of the comparison experiments , since the inputs of HumanGAN and other models are not human parsing and clothes texture attributes. Looking forward to you helping me clarify my doubts! Thanks!

[yumingj]

Thanks for your interest in our work! We adapt the comparison methods into the same setting as our method. For example, for HumanGAN, we implement two versions: 1) Taking the human parsing and attributes as inputs (Table 1), 2) Taking human pose and attributes as inputs (Table 2).

Hope the answers address your concerns! Thanks!

[gouchaonijiao]

Thans a lot for your detailed introduction,I sincerely appreciate your work and the dataset you made.By the way, how should I do the experiments if their code is not open-source like HumanGAN?