SPIGA: Shape Preserving Facial Landmarks with Graph Attention Networks.
Source code of SPIGA, a face alignment and headpose estimator that takes advantage of the complementary benefits from CNN and GNN architectures producing plausible face shapes in presence of strong appearance changes.
Beta Release including:
* SPIGA Models
* Inference Framework
* Face Video Analyzer Demo
* Dataloaders and Visualizers
* Benchmark and SPIGA Evaluation
* Colab Tutorials