Learning Spectral Unions of Partial Deformable 3D Shapes
Abstract
Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study of the Laplacian spectrum as a compact, isometry and permutation-invariant representation of a shape. Some recent works show how the intrinsic geometry of a full shape can be recovered from its spectrum, but there are approaches that consider the more challenging problem of recovering the geometry from the spectral information of partial shapes. In this paper, we propose a possible way to fill this gap. We introduce a learning-based method to estimate the Laplacian spectrum of the union of partial non-rigid 3D shapes, without actually computing the 3D geometry of the union or any correspondence between those partial shapes. We do so by operating purely in the spectral domain and by defining the union operation between short sequences of eigenvalues. We show that the approximated union spectrum can be used as-is to reconstruct the complete geometry [MRC*19], perform region localization on a template [RTO*19] and retrieve shapes from a database, generalizing ShapeDNA [RWP06] to work with partialities. Working with eigenvalues allows us to deal with unknown correspondence, different sampling, and different discretizations (point clouds and meshes alike), making this operation especially robust and general. Our approach is data-driven and can generalize to isometric and non-isometric deformations of the surface, as long as these stay within the same semantic class (e.g., human bodies or horses), as well as to partiality artifacts not seen at training time.
BibTeX
@article {10.1111:cgf.14483,
journal = {Computer Graphics Forum},
title = {{Learning Spectral Unions of Partial Deformable 3D Shapes}},
author = {Moschella, Luca and Melzi, Simone and Cosmo, Luca and Maggioli, Filippo and Litany, Or and Ovsjanikov, Maks and Guibas, Leonidas and Rodolà, Emanuele},
year = {2022},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.14483}
}
journal = {Computer Graphics Forum},
title = {{Learning Spectral Unions of Partial Deformable 3D Shapes}},
author = {Moschella, Luca and Melzi, Simone and Cosmo, Luca and Maggioli, Filippo and Litany, Or and Ovsjanikov, Maks and Guibas, Leonidas and Rodolà, Emanuele},
year = {2022},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.14483}
}
Collections
Related items
Showing items related by title, author, creator and subject.
-
Rational Bézier Guarding
Khanteimouri, Payam; Mandad, Manish; Campen, Marcel (The Eurographics Association and John Wiley & Sons Ltd., 2022)We present a reliable method to generate planar meshes of nonlinear rational triangular elements. The elements are guaranteed to be valid, i.e. defined by injective rational functions. The mesh is guaranteed to conform ... -
Educative Visuals - Digital Delivery of Architectural Information for (potential) Heritage Buildings
Kwee, Verdy; Radford, Antony; Bruton, Dean (The Eurographics Association, 2006)The paper proposes models that address current issues and considerations at several key levels relating to treatment of architectural information, its presentation and delivery methods specific to architecture education ... -
RePiX VR - Learning environment for the Rendering Pipeline in Virtual Reality
Heinemann, Birte; Görzen, Sergej; Schroeder, Ulrik (The Eurographics Association, 2022)Virtual reality can be used to support computer graphics teaching, e.g. by offering the chance to illustrate 3D processes that are difficult to convey. This paper describes the development and first evaluations of RePiX ...