Has anyone tried modifying an RGB camera to an RGB-D camera in ACT?
Has anyone tried modifying an RGB camera to an RGB-D camera in ACT?
Regarding the conditioning mechanism in act\vae models, theoretically any type of information can be incorporated as conditional input. You could modify the architecture to integrate depth information by extending the existing conditioning framework, potentially through additional embedding layers or concatenation operations in the network's feature space.
Thanks bro
Thanks for subscribing!
This email has been registered!