Questions between Affine-invariant Pointmap and Metric Scale Supervision
Nobody has claimed this yet.
- Dominant language
- JavaScript
- Stars
- 3k
- Forks
- 234
- PR merge metrics
- No merged PRs in 30d
Description
Hi, thanks for the great work! I have a question regarding the geometric constraints used in your training process.
As I understand it:
-
The model predicts an affine-invariant pointmap, which allows for arbitrary scale ($s$) and shift ($t$).
-
During training, the model predicts a single scale factor to recover the metric geometry.
My confusion is: if the pointmap is truly affine-invariant, then to recover the original metric geometry, shouldn’t the model predict both a scale and a shift?
Alternatively, should the pointmap itself be trained to be scale-invariant only, so that predicting a single scale is sufficient?
Thanks in advance for your time!
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
Start with the geometric-constraint description in issue #145 and review how the model's affine-invariant pointmap and metric-scale supervision are defined. Resolve whether recovering metric geometry requires both scale and shift, or whether the pointmap is intended to be scale-invariant only. Done means the distinction and training behavior are clearly documented.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100