search

robotgradient / grasp_diffusion

Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home
MIT License
234 stars 24 forks source link

some question about loss function #11

Open o0stinger0o opened 8 months ago

o0stinger0o commented 8 months ago

Hello author @TheCamusean This is really a great job, but I have some questions about the loss function. What is the difference between ProjectedSE3DenoisingLoss and SE3DenoisingLoss. The loss mentioned in the paper should be SE3DenoisingLoss, but I saw that most of the configuration files in the experiment used ProjectedSE3DenoisingLoss.

Another question is what is the necessity of learning SDF, because I don’t know SDF very well, is it just to improve the quality of generation?

toannguyen1904 commented 5 months ago

Same question from me, can the authors please explain the SE3DenoisingLoss loss function?