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

Mesh generation of a moving vehicle at every frame of the video sequence recorded from another moving object #169

Open
Tuhin-nd opened this issue Sep 25, 2024 · 1 comment

Comments

@Tuhin-nd
Copy link

Tuhin-nd commented Sep 25, 2024

哥儿 @wing-kit @wenbowen123, Awesome work indeed!

I have few questions, would highly appreciate your response -

  • Will BundleSDF be able to properly built mesh representations of the object at every instance of the video?

  • Scene: Both camera (ego vehicle) and some other target vehicle are moving. Maximum distance of the target vehicle can be at most 50 metres. I gave the segmentation masks of the target vehicle along with rgb and depth as input - will BundleSDF be able to produce mesh of the object at each frame with correct pose and orientation 6D?

@wenbowen123
Copy link
Collaborator

  • if you have RGBD and instance masks for each of them, then it should be feasible
  • Again, if you have depth and masks, it should be feasible. But since this is a driving scene, there are some params that need to be adapted such as farthest depth clipping.

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