A Robust Multilinear Model Learning Framework for 3D Faces - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

A Robust Multilinear Model Learning Framework for 3D Faces


Multilinear models are widely used to represent the statistical variations of 3D human faces as they decouple shape changes due to identity and expression. Existing methods to learn a multilinear face model degrade if not every person is captured in every expression, if face scans are noisy or partially occluded, if expressions are erroneously labeled, or if the vertex correspondence is inaccurate. These limitations impose requirements on the training data that disqualify large amounts of available 3D face data from being usable to learn a multilinear model. To overcome this, we introduce the first framework to robustly learn a multilinear model from 3D face databases with missing data, corrupt data, wrong semantic correspondence , and inaccurate vertex correspondence. To achieve this robustness to erroneous training data, our framework jointly learns a multilinear model and fixes the data. We evaluate our framework on two publicly available 3D face databases, and show that our framework achieves a data completion accuracy that is comparable to state-of-the-art tensor completion methods. Our method reconstructs corrupt data more accurately than state-of-the-art methods, and improves the quality of the learned model significantly for erroneously labeled expressions.
Fichier principal
Vignette du fichier
incomplete_registration_optimization_final.pdf (6.05 Mo) Télécharger le fichier
SupplementaryVideo.avi (9.14 Mo) Télécharger le fichier
rmm-framework.zip (20.26 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Video
Origin : Files produced by the author(s)
Comment : Data of trained models that allows to reproduce the results presented in the paper.

Dates and versions

hal-01290783 , version 1 (18-03-2016)



Timo Bolkart, Stefanie Wuhrer. A Robust Multilinear Model Learning Framework for 3D Faces. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016, Las Vegas, United States. pp.4911-4919, ⟨10.1109/CVPR.2016.531⟩. ⟨hal-01290783⟩
440 View
741 Download



Gmail Facebook X LinkedIn More