Spectral Shape Recovery and Analysis Via Data-driven Connections

We introduce a novel learning-based method to recover shapes from their Laplacian spectra, based on establishing and exploring connections in a learned latent space. The core of our approach consists in a cycle-consistent module that maps between a learned latent space and sequences of eigenvalues....

Descripción completa

Detalles Bibliográficos
Autores principales: Marin, Riccardo, Rampini, Arianna, Castellani, Umberto, Rodolà, Emanuele, Ovsjanikov, Maks, Melzi, Simone
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer US 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550494/
https://www.ncbi.nlm.nih.gov/pubmed/34720402
http://dx.doi.org/10.1007/s11263-021-01492-6

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550494/
https://www.ncbi.nlm.nih.gov/pubmed/34720402
http://dx.doi.org/10.1007/s11263-021-01492-6

Ejemplares similares