shalfun / DrivingDiffusion

Layout-Guided multi-view driving scene video generation with latent diffusion model
MIT License
561 stars 15 forks source link

How do you encode 3D Layout to rgb image #3

Open CSU-NXY opened 1 year ago

CSU-NXY commented 1 year ago

Hi, the paper says that the road-structure information, the target category, and the target instance ID corresponding to each pixel is incorporated and encoded into RGB values. Can you explain more about how to do it?

Primer-1-wy commented 2 weeks ago

I would like to ask the same question as well about how to encode the 3D lay out information into RGB images.Thanks!!!