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 FRGCv2

(using a model trained on FRGCv1)

In this experiment we target 14 landmarks on 4007 facial scans from FRGCv2, while the model is trained on 943 scans from FRGCv1, obtaining an average accuracy of 3.65 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 1.61 and 1.94 mm)

166

299

456

977

1332

1341

1706

2293

2520

2557

 

Average performing cases (overall errors ~ 3.65 mm)

18

41

480

616

638

763

1002

1131

1505

1732

1950

2139

2538

2666

2894

2955

3303

3565

3700

3954

 

The 10 cases with highest errors (between 8.27 and 13.51 mm)

31

131

146

1377

1395

2332

2712

2760

3114

3769

 

 

 

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