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

How are the reference frames chosen during training?

Open
#153 2 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 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.