search

dunbar12138 / pix2pix3D

pix2pix3D: Generating 3D Objects from 2D User Inputs
http://www.cs.cmu.edu/~pix2pix3D/
MIT License
1.65k stars 132 forks source link

about the discriminator #16

Open cocoaw opened 1 year ago

cocoaw commented 1 year ago

hi,thank you for your great work, can i ask your discriminator architecture?It seems that you just use the reconstruction loss about image and mask to constrain the input and output mask shape,how about the reconstruction loss doesn't work well ?do you have any discriminator about the constrain between input and mask shape?

dunbar12138 commented 1 year ago

Hi, we have 2 discriminators, whose structures are similar to EG3D, one only takes RGB as input, and the other takes RGB + label map as input. Please check our paper for more details.