Instant recovery of shape from spectrum via latent space connections

Riccardo Marin, Arianna Rampini, Umberto Castellani, Emanuele Rodola, Maks Ovsjanikov, Simone Melzi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 super-resolution, shape exploration, style transfer, spectrum estimation from point clouds, segmentation transfer and point-to-point matching.
Original languageEnglish (US)
Title of host publication2020 International Conference on 3D Vision (3DV)
PublisherIEEE
Pages120-129
Number of pages10
ISBN (Print)9781728181288
DOIs
StatePublished - Nov 2020
Externally publishedYes

Fingerprint

Dive into the research topics of 'Instant recovery of shape from spectrum via latent space connections'. Together they form a unique fingerprint.

Cite this