SRILF Examples

All Examples

        Examples on FRGC v1 with 2-fold cross-validation

        Examples on FRGC v2 with 2-fold cross-validation

        Examples on FRGC v2 using a model trained on FRGC v1

 

SRILF Examples on FRGCv1

(2-fold cross validation)

In this experiment we target 14 landmarks on 943 facial scans, split into training and test set by 2-fold cross validation, obtaining an average accuracy of 3.44 mm (error over all landmarks with respect to manual ground truth). We provide below a set of examples, separated into 3 categories:

         The 10 cases with lowest overall errors

         Average performing cases (the 20 cases with overall errors closest to the average accuracy obtained in this experiment)

         The 10 cases with highest overall errors

 

The 10 cases with lowest errors (between 1.63 and 2.06 mm)

39

159

243

695

761

798

809

832

876

898

 

Average performing cases (overall errors ~ 3.44 mm)

134

136

141

168

240

353

378

384

399

426

684

690

862

868

883

892

917

925

927

936

 

The 10 cases with highest errors (between 5.79 and 7.76 mm)

72

75

228

507

643

674

675

713

715

829

 

 

All Examples

        Examples on FRGC v1 with 2-fold cross-validation

        Examples on FRGC v2 with 2-fold cross-validation

        Examples on FRGC v2 using a model trained on FRGC v1