Hacker News new | ask | show | jobs
by neilxm 968 days ago
That’s the idea for next steps.

Basically if you generate a backdrop and then estimate light direction you can inverse render that onto the 3d model given all the depth information you get for free from the model

1 comments

You should be able to do relighting with ControlNet. Basically render the model to all the maps you'd use for PBR (fullbright color/depth/reflectivity/etc), train ControlNets that hold all those constant and do img2img but let it make up the background.

Though I'm not aware of anyone already doing this, since I think research has moved on to NeRF models that act on 3D scenes directly.