Reconstructing Recognizable 3D Face Shapes based on 3D Morphable Models

Simple item page
dc.contributor.authorJiang, Diqiongen_US
dc.contributor.authorJin, Yiweien_US
dc.contributor.authorZhang, Fang‐Lueen_US
dc.contributor.authorLai, Yu‐Kunen_US
dc.contributor.authorDeng, Rishengen_US
dc.contributor.authorTong, Ruofengen_US
dc.contributor.authorTang, Minen_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2022-10-11T05:24:58Z
dc.date.available2022-10-11T05:24:58Z
dc.date.issued2022
dc.description.abstractMany recent works have reconstructed distinctive 3D face shapes by aggregating shape parameters of the same identity and separating those of different people based on parametric models (e.g. 3D morphable models (3DMMs)). However, despite the high accuracy in the face recognition task using these shape parameters, the visual discrimination of face shapes reconstructed from those parameters remains unsatisfactory. Previous works have not answered the following research question: Do discriminative shape parameters guarantee visual discrimination in represented 3D face shapes? This paper analyses the relationship between shape parameters and reconstructed shape geometry, and proposes a novel shape identity‐aware regularization (SIR) loss for shape parameters, aiming at increasing discriminability in both the shape parameter and shape geometry domains. Moreover, to cope with the lack of training data containing both landmark and identity annotations, we propose a network structure and an associated training strategy to leverage mixed data containing either identity or landmark labels. In addition, since face recognition accuracy does not mean the recognizability of reconstructed face shapes from the shape parameters, we propose the SIR metric to measure the discriminability of face shapes. We compare our method with existing methods in terms of the reconstruction error, visual discriminability, and face recognition accuracy of the shape parameters and SIR metric. Experimental results show that our method outperforms the state‐of‐the‐art methods. The code will be released at .en_US
dc.description.number6
dc.description.sectionheadersMajor Revision from Pacific Graphics
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14513
dc.identifier.issn1467-8659
dc.identifier.pages348-364
dc.identifier.urihttps://doi.org/10.1111/cgf.14513
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14513
dc.publisher© 2022 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.subjectfacial modelling
dc.subjectmodelling
dc.titleReconstructing Recognizable 3D Face Shapes based on 3D Morphable Modelsen_US
Files
Collections
41-Issue 6