ByteDance-Seed / ByteDance-Seed/Depth-Anything-3
Does providing multi-view camera intrinsic parameters improve the accuracy of pose estimation?
Open
- Dominant language
- Python
- Stars
- 6.3k
- Forks
- 702
- PR merge metrics
- No merged PRs in 30d
Description
I am currently testing DA3NESTED-GIANT-LARGE-1.1.
I noticed that providing camera intrinsic parameters does not seem to change the pose estimation results compared to not providing them.
Is this expected behavior?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.