ByteDance-Seed / ByteDance-Seed/Depth-Anything-3
About the distance-weights of the surface-normal loss
Open
- Dominant language
- Python
- Stars
- 6.3k
- Forks
- 702
- PR merge metrics
- No merged PRs in 30d
Description
In the distance-weighted surface-normal loss, are the distance weights computed from the predicted point map kept attached to the computation graph, or are they detached?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.