deepinsight / deepinsight/insightface
how to unify menpo landmarks?
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
according to the paper “Cascade Multi-view Hourglass Model for Robust 3D Face Alignment”，the author unifys both semi-frontal (68 landmarks) and profile (39landmarks) representation. is there any one know the algorithm？
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no repository file, test, or entry point. Start by reading the cited paper's landmark-unification method and comparing it with the repository's face-alignment work; done means documenting a verified algorithm or implementation path for combining the 68- and 39-landmark representations.
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