# SPIGA: Shape Preserving Facial Landmarks with Graph Attention Networks.


This repository contains the models weights 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. 

<p align="center">
    <img src="https://raw.githubusercontent.com/andresprados/SPIGA/main/assets/spiga_scheme.png" width="80%">
</p>


## Setup
The repository is available on [github](https://github.com/andresprados/SPIGA.git)

## Results

<details>
  <summary> WFLW Dataset </summary>

|[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/shape-preserving-facial-landmarks-with-graph/face-alignment-on-wflw)](https://paperswithcode.com/sota/face-alignment-on-wflw?p=shape-preserving-facial-landmarks-with-graph)|NME_ioc|AUC_10|FR_10|NME_P90|NME_P95|NME_P99|
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|full|4.060|60.558|2.080|6.766|8.199|13.071|
|pose|7.141|35.312|11.656|10.684|13.334|26.890|
|expression|4.457|57.968|2.229|7.023|8.148|22.388|
|illumination|4.004|61.311|1.576|6.528|7.919|11.090|
|makeup|3.809|62.237|1.456|6.320|8.289|11.564|
|occlusion|4.952|53.310|4.484|8.091|9.929|16.439|
|blur|4.650|55.310|2.199|7.311|8.693|14.421|
</details>
    
<details>
  <summary> MERLRAV Dataset </summary>
    
|[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/shape-preserving-facial-landmarks-with-graph/face-alignment-on-merl-rav)](https://paperswithcode.com/sota/face-alignment-on-merl-rav?p=shape-preserving-facial-landmarks-with-graph)|NME_bbox|AUC_7|FR_7|NME_P90|NME_P95|NME_P99|
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|full|1.509|78.474|0.052|2.163|2.468|3.456|
|frontal|1.616|76.964|0.091|2.246|2.572|3.621|
|half_profile|1.683|75.966|0.000|2.274|2.547|3.397|
|profile|1.191|82.990|0.000|1.735|2.042|2.878|
</details>

<details>
  <summary> 300W Private Dataset </summary>
    
|[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/shape-preserving-facial-landmarks-with-graph/face-alignment-on-300w-split-2)](https://paperswithcode.com/sota/face-alignment-on-300w-split-2?p=shape-preserving-facial-landmarks-with-graph)|NME_bbox|AUC_7|FR_7|NME_P90|NME_P95|NME_P99|
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|full|2.031|71.011|0.167|2.788|3.078|3.838|
|indoor|2.035|70.959|0.333|2.726|3.007|3.712|
|outdoor|2.027|37.174|0.000|2.824|3.217|3.838|
</details>

<details>
  <summary> COFW68 Dataset </summary>

|[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/shape-preserving-facial-landmarks-with-graph/face-alignment-on-cofw-68)](https://paperswithcode.com/sota/face-alignment-on-cofw-68?p=shape-preserving-facial-landmarks-with-graph)|NME_bbox|AUC_7|FR_7|NME_P90|NME_P95|NME_P99|
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|full|2.517|64.050|0.000|3.439|4.066|5.558|
</details>

<details>
  <summary> 300W Public Dataset </summary>

|[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/shape-preserving-facial-landmarks-with-graph/face-alignment-on-300w)](https://paperswithcode.com/sota/face-alignment-on-300w?p=shape-preserving-facial-landmarks-with-graph)|NME_ioc|AUC_8|FR_8|NME_P90|NME_P95|NME_P99|
|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|full|2.994|62.726|0.726|4.667|5.436|7.320|
|common|2.587|44.201|0.000|3.710|4.083|5.215|
|challenge|4.662|42.449|3.704|6.626|7.390|10.095|

</details>


## BibTeX Citation
```
@inproceedings{Prados-Torreblanca_2022_BMVC,
  author    = {Andrés  Prados-Torreblanca and José M Buenaposada and Luis Baumela},
  title     = {Shape Preserving Facial Landmarks with Graph Attention Networks},
  booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
  publisher = {{BMVA} Press},
  year      = {2022},
  url       = {https://bmvc2022.mpi-inf.mpg.de/0155.pdf}
}
```