Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Diffusion policy's RGB encoder shared by all cameras. Is this intended? #483

Open
HiroIshida opened this issue Oct 22, 2024 · 1 comment

Comments

@HiroIshida
Copy link

In the diffusion policy implementation, it seems that RGB encoder is shared by all camera images.

self.rgb_encoder = DiffusionRgbEncoder(config)

However, in the original paper, different image encoders are used for different cameras.
image

@alexander-soare Is this design choice? (e.g. single encoder is better than multiple encoders?)

Chi, Cheng, et al. "Diffusion policy: Visuomotor policy learning via action diffusion." The International Journal of Robotics Research (2023): 02783649241273668.

@alexander-soare
Copy link
Collaborator

@HiroIshida thanks for raising this. It was a choice for simple over complicated, mostly for speed of development. We're not against using multiple image encoders going forward.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants