We introduce the first learning-based method for recovering shapes from Laplacian spectra. Our model consists of a cycle-consistent module that maps between learned latent vectors of an auto-encoder and sequences of eigenvalues. This module provides an efficient and effective linkage between Laplacian spectrum and geometry. Our data-driven approach replaces the need for ad-hoc regularizers required by prior methods, while providing more accurate results at a fraction of the computational cost. Our learning model applies without modifications across different dimensions (2D and 3D shapes alike), representations (meshes, contours and point clouds), as well as across different shape classes, and admits arbitrary resolution of the input spectrum without affecting complexity. The increased flexibility allows us to address notoriously difficult tasks in 3D vision and geometry processing within a unified framework, including shape generation from spectrum, mesh superresolution, shape exploration, style transfer, spectrum estimation from point clouds, segmentation transfer and pointtopoint matching.
Instant recovery of shape from spectrum via latent space connections / Marin, R; Rampini, A; Castellani, U; Rodolà, E; Ovsjanikov, M; Melzi, S. - (2020), pp. 120-129. (Intervento presentato al convegno International Conference on 3D Vision (3DV) tenutosi a Online) [10.1109/3DV50981.2020.00022].
Instant recovery of shape from spectrum via latent space connections
Marin R;Rampini A;Rodolà E;Melzi S
2020
Abstract
We introduce the first learning-based method for recovering shapes from Laplacian spectra. Our model consists of a cycle-consistent module that maps between learned latent vectors of an auto-encoder and sequences of eigenvalues. This module provides an efficient and effective linkage between Laplacian spectrum and geometry. Our data-driven approach replaces the need for ad-hoc regularizers required by prior methods, while providing more accurate results at a fraction of the computational cost. Our learning model applies without modifications across different dimensions (2D and 3D shapes alike), representations (meshes, contours and point clouds), as well as across different shape classes, and admits arbitrary resolution of the input spectrum without affecting complexity. The increased flexibility allows us to address notoriously difficult tasks in 3D vision and geometry processing within a unified framework, including shape generation from spectrum, mesh superresolution, shape exploration, style transfer, spectrum estimation from point clouds, segmentation transfer and pointtopoint matching.File | Dimensione | Formato | |
---|---|---|---|
Marin_Instant _2020.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
394.45 kB
Formato
Adobe PDF
|
394.45 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.