Presentation / Installation


Unsupervised Learning of Robust Spectral Shape Matching
SessionMarvelous Mappings
DescriptionWe present an unsupervised method for robust spectral shape matching by explicitly considering the relation between functional and point-wise maps. Our method does not require dataset-specific customizations and substantially outperforms previous state-of-the-art methods on various challenging shape-matching benchmarks, including non-isometric, topologically noisy, partial, and anisotropic meshed shape pairs.
Authors
Dongliang Cao
University of Bonn
Paul Roetzer
University of Bonn
Florian Bernard
University of Bonn
Event Type
Technical Paper
TimeThursday, 10 August 20239:44am - 9:55am PDT
LocationRoom 502 AB
ACM Digital Library Technical Papers pdfs
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Thursday, 10 August 20239am - 10:30am PDTRoom 502 AB
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Modeling
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
An Elastic Basis for Spectral Shape Correspondence