Open 013292 opened 1 year ago
I suppose it would be possible, yes. You could modify the code to load multiple conditioning images and their corresponding camera positions. That being said, if you already have a mesh model, what is the motivation for wanting to do RealFusion?
I have a .vtp 3d mesh model, and 2d rendered images in different views. Is it possible to train the real fusion based on such data? Thank you :-)