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

Feature request: Visualizing training poses along with 3DGS model #297

Open
hardikdava opened this issue Nov 21, 2024 · 5 comments
Open

Comments

@hardikdava
Copy link

Hello devs, great work for developing great tool. It would be good to also have an option to upload training camera poses to Supersplat for analysis or debugging purpose. Then camera fly mode will take these cameras to create a trajectory or something similar.

@slimbuck
Copy link
Member

Hi @hardikdava,

Which file format of camera poses would you like to import?

We already support cameras.json format, which is generated by the inria tools. See the CAMERA POSES panel on the right. There you can also add the current camera to the list.

Screenshot 2024-11-21 at 09 04 52

We'll be adding support for more formats as users request though, so be sure to let me know which format you prefer.

Thanks!

@hardikdava
Copy link
Author

@slimbuck Ideally, it would great to support for nerfstudio format. It is one of the common trainer that community use.

@slimbuck
Copy link
Member

I actually have a branch with this code in the works already. I might take another look at it and try get this out in the next week.

@hardikdava
Copy link
Author

Thanks for consideration.

@hardikdava
Copy link
Author

@slimbuck A camera frame with frustum would be good for final visualization.

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