Facial Landmark Localization
A computer vision study that turns a FaceXFormer survey into experiments, notebooks, and a documented evaluation path.
The problem
Locate characteristic points on a face and understand the model architecture behind those predictions.
The approach
The project surveys related work, studies FaceXFormer, and documents smaller-dataset experiments and autocast use.
Available materials
The repository includes research materials, reports, slides, source code, and evaluation notebooks using Python, PyTorch, Jupyter, and Streamlit.
Contribution & context
Contributor in a four-person project team.
Scope of this project summary
The public README describes the experimental scope. No numerical performance claim or individual ownership of a component is asserted here.