ByteDance-Seed / ByteDance-Seed/Depth-Anything-3
Why is the camera encoder/decoder model block invoked to re-predict the intrinsic and extrinsic parameters when specifying them?
Open
- Dominant language
- Python
- Stars
- 6.3k
- Forks
- 702
- PR merge metrics
- No merged PRs in 30d
Description
In the code:
(1) Why is the camera encoder/decoder model block invoked to re-predict the intrinsic and extrinsic parameters when specifying them?
(2) Didn’t the paper recover the camera intrinsic and extrinsic parameters using ray information and point out that directly predicting the camera intrinsic and extrinsic parameters fails to satisfy the orthogonality constraint?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.