3DPointCaps++: Learning 3D Representations with Capsule Networks

We present 3DPointCaps++ for learning robust, flexible and generalizable 3D object representations without requiring heavy annotation efforts or supervision. Unlike conventional 3D generative models, our algorithm aims for building a structured latent space where certain factors of shape variations,...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Yongheng, Fang, Guangchi, Guo, Yulan, Guibas, Leonidas, Tombari, Federico, Birdal, Tolga
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer US 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9362689/
https://www.ncbi.nlm.nih.gov/pubmed/35968252
http://dx.doi.org/10.1007/s11263-022-01632-6

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9362689/
https://www.ncbi.nlm.nih.gov/pubmed/35968252
http://dx.doi.org/10.1007/s11263-022-01632-6

Ejemplares similares