We propose Vid-LLM for versatile 3D scene understanding. The framework does not rely on dense 3D inputs or prior poses, making it practical for real-world deployment.
The code will be released upon the acceptance of the paper.
-
Notifications
You must be signed in to change notification settings - Fork 0
chenhaijier/Vid-LLM
About
We propose Vid-LLM for versatile 3D scene understanding. The framework does not rely on dense 3D inputs or prior poses, making it practical for real-world deployment.
Resources
Stars
Watchers
Forks
Packages 0
No packages published