Hi @liren2515 Thanks for open-sourcing this awesome work. I have a question about fitting a 3D garment mesh or an image using DrapeNet. As far as I understand, this is done by freezing the decoder and optimizing a latent code. However, what if the latent code goes out of distribution the latent space ? For example, in the images below, the optimized mesh has some floaters:
Hi @liren2515 Thanks for open-sourcing this awesome work. I have a question about fitting a 3D garment mesh or an image using DrapeNet. As far as I understand, this is done by freezing the decoder and optimizing a latent code. However, what if the latent code goes out of distribution the latent space ? For example, in the images below, the optimized mesh has some floaters: