Pretrained model without Rendered people

[jseobyun]

Hello, thank you for sharing this amazing work.

HDNet (trained by 34,000 RenderedPeople images and 100,000 Tiktok images) performance is very impressive compared to previous works :)

After reading the paper, I became curious about the performance of HDNet trained without RenderedPeople and with fewer RenderedPeople

Do you have pre-trained HDNet of those cases? or the results?

[yasaminjafarian]

Hi. Thanks a lot for your message. This work is trained in a semi-supervised framework therefore having the RenderPeople data is important. We unfortunately don't have the pre-trained model for a smaller amount of RenderPeople.

[jseobyun]

Thanks!