ByteDance-Seed / ByteDance-Seed/Depth-Anything-3
How are the reference frames chosen during training?
Open
- Dominant language
- Python
- Stars
- 6.3k
- Forks
- 702
- PR merge metrics
- No merged PRs in 30d
Description
I have a question about the reference frame selection during the training phase: Could you explain how the reference frames are selected? This information seems to be omitted or not clearly specified in the publication
Contributor guide
No contributing guide indexed for this repository
Research direction
Review the training-phase description and the publication referenced in the issue, then identify where reference-frame selection is documented or implemented. The work is done when the selection process is clearly explained and the omission from the publication or project documentation is addressed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100