Show simple item record

dc.contributor.authorLiu, Shengjunen_US
dc.contributor.authorXu, Haojunen_US
dc.contributor.authorYan, Dong-Mingen_US
dc.contributor.authorHu, Lingen_US
dc.contributor.authorLiu, Xinruen_US
dc.contributor.authorLi, Qinsongen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:39:28Z
dc.date.available2022-10-04T06:39:28Z
dc.date.issued2022
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14656
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14656
dc.description.abstractWe propose a novel unsupervised learning approach for computing correspondences between non-rigid 3D shapes. The core idea is that we integrate a novel structural constraint into the deep functional map pipeline, a recently dominant learning framework for shape correspondence, via a powerful spectral manifold wavelet transform (SMWT). As SMWT is isometrically invariant operator and can analyze features from multiple frequency bands, we use the multiscale SMWT results of the learned features as function preservation constraints to optimize the functional map by assuming each frequency-band information of the descriptors should be correspondingly preserved by the functional map. Such a strategy allows extracting significantly more deep feature information than existing approaches which only use the learned descriptors to estimate the functional map. And our formula strongly ensure the isometric properties of the underlying map. We also prove that our computation of the functional map amounts to filtering processes only referring to matrix multiplication. Then, we leverage the alignment errors of intrinsic embedding between shapes as a loss function and solve it in an unsupervised way using the Sinkhorn algorithm. Finally, we utilize DiffusionNet as a feature extractor to ensure that discretization-resistant and directional shape features are produced. Experiments on multiple challenging datasets prove that our method can achieve state-of-the-art correspondence quality. Furthermore, our method yields significant improvements in robustness to shape discretization and generalization across the different datasets. The source code and trained models will be available at https://github.com/HJ-Xu/ WTFM-Layer.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Shape analysis; Matching
dc.subjectComputing methodologies → Shape analysis
dc.subjectMatching
dc.titleWTFM Layer: An Effective Map Extractor for Unsupervised Shape Correspondenceen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersCurves and Meshes
dc.description.volume41
dc.description.number7
dc.identifier.doi10.1111/cgf.14656
dc.identifier.pages51-61
dc.identifier.pages11 pages


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • 41-Issue 7
    Pacific Graphics 2022 - Symposium Proceedings

Show simple item record