Conference paper · Book chapter · Preprint article
Multi-view Consensus CNN for 3D Facial Landmark Placement
Department of Applied Mathematics and Computer Science, Technical University of Denmark1
Visual Computing, Department of Applied Mathematics and Computer Science, Technical University of Denmark2
Technical University of Denmark3
Center for Biological Sequence Analysis, Department of Systems Biology, Technical University of Denmark4
Mental Health Centre Sct. Hans5
Rigshospitalet6
The rapid increase in the availability of accurate 3D scanning devices has moved facial recognition and analysis into the 3D domain. 3D facial landmarks are often used as a simple measure of anatomy and it is crucial to have accurate algorithms for automatic landmark placement. The current state-of-the-art approaches have yet to gain from the dramatic increase in performance reported in human pose tracking and 2D facial landmark placement due to the use of deep convolutional neural networks (CNN).
Development of deep learning approaches for 3D meshes has given rise to the new subfield called geometric deep learning, where one topic is the adaptation of meshes for the use of deep CNNs. In this work, we demonstrate how methods derived from geometric deep learning, namely multi-view CNNs, can be combined with recent advances in human pose tracking.
The method finds 2D landmark estimates and propagates this information to 3D space, where a consensus method determines the accurate 3D face landmark position. We utilise the method on a standard 3D face dataset and show that it outperforms current methods by a large margin. Further, we demonstrate how models trained on 3D range scans can be used to accurately place anatomical landmarks in magnetic resonance images.
Language: | English |
---|---|
Publisher: | Springer |
Year: | 2019 |
Pages: | 706-719 |
Proceedings: | 14th Asian Conference on Computer Vision |
Series: | Lecture Notes in Computer Science |
Journal subtitle: | 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part I |
ISBN: | 3030208869 , 3030208877 , 9783030208868 and 9783030208875 |
ISSN: | 03029743 and 16113349 |
Types: | Conference paper , Book chapter and Preprint article |
DOI: | 10.1007/978-3-030-20887-5_44 |
ORCIDs: | Paulsen, Rasmus Reinhold , Juhl, Kristine Aavild , Einarsson, Gudmundur , 0000-0002-9120-8098 , 0000-0001-6703-7762 and 0000-0002-3172-9246 |