About training supervision for depth values
Nobody has claimed this yet.
- Dominant language
- JavaScript
- Stars
- 3k
- Forks
- 234
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
Excellent work, thanks for the detailed paper and prompt model release! I found the paper very insightful, and the results are remarkable across various datasets and tasks.
I have a question regarding the supervision signals used during training, particularly for depth values.
Whether the training process used relative depth ground truth (affine-invariant) or absolute metric depth for supervision?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue concerns training supervision for depth values in MoGe. Start by checking the detailed paper and prompt model release for whether supervision used affine-invariant relative depth or absolute metric depth. Done when the answer is provided or documented.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100