ByteDance-Seed / ByteDance-Seed/Depth-Anything-3

Does providing multi-view camera intrinsic parameters improve the accuracy of pose estimation?

Open
#229 0 comments 0 reactions 0 assignees View on GitHub
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.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.