Initial Steps towards a Multilevel Functional Principal Components Analysis Model of Dynamical Shape Changes. DJJ Farnell, P Claes.

Multilevel PCA (mPCA) has been used by us to analyze 3D facial shapes obtained from 3D facial scans; note that two-level multilevel PCA (mPCA) is equivalent to bgPCA. mPCA has been used previously to investigate changes by ethnicity and sex, facial shape changes in adolescents due to age, and the effects of maternal smoking and alcohol consumption on the facial shape of English adolescents.

Articulated Objects in Free-form Hand Interaction. Z Fan, O Taheri, D Tzionas, M Kocabas, M Kaufmann, MJ Black, O Hilliges.

Introducing ARCTIC – the first dataset of free-form interactions of hands and articulated objects. ARCTIC has 1.2M images paired with accurate 3D meshes for both hands and for objects that move and deform over time. The dataset also provides hand-object contact information.

Projection-wise Disentangling for Fair and Interpretable Representation Learning: Application to 3D Facial Shape Analysis. X Liu, B Li, E Bron, W Niessen, E Wolvius, G Roshchupkin.

The proposed method was evaluated on the analysis of 3D facial shape and patient characteristics (N=5011). Experiments showed that this conceptually simple method achieved state-of-the-art fair prediction performance and interpretability, showing its great potential for clinical applications.

3D human tongue reconstruction from single “in-the-wild” images. S Ploumpis, S Moschoglou, V Triantafyllou, S Zafeiriou.

In this work, we presented the first pipeline which is able to perform 3D head and tongue reconstruction from a single image. To achieve this, we collected the first diverse tongue dataset with various tongue shapes and positions which we make publicly available to the research community.