L
Leonidas J. Guibas
Researcher at Stanford University
Publications - 736
Citations - 99526
Leonidas J. Guibas is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Point cloud. The author has an hindex of 124, co-authored 691 publications receiving 79200 citations. Previous affiliations of Leonidas J. Guibas include PARC & Association for Computing Machinery.
Papers
More filters
Posted Content
Representation Learning Through Latent Canonicalizations
TL;DR: In this paper, the authors propose to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision, by modifying the value of a factor to a pre-determined canonical value.
Journal ArticleDOI
3DPointCaps++: Learning 3D Representations with Capsule Networks
TL;DR: 3DPointCaps++ as mentioned in this paper uses deconvolution operators to reconstruct 3D points in a self-supervised manner and introduces a cluster loss ensuring that the points reconstructed by a single capsule remain local and do not spread across the object uncontrollably.
Journal ArticleDOI
Compressive Network Analysis
TL;DR: In this article, a new framework for modeling network data, which connects two seemingly different areas: network data analysis and compressed sensing, is presented, and the authors consider the network clique detection problem and show connections between their formulation with a new algebraic tool.
Posted ContentDOI
Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization
Connor Z. Lin,Koki Nagano,Jan Kautz,Eric R. Chan,Umar Iqbal,Leonidas J. Guibas,Gordon Wetzstein,Sameh Khamis +7 more
TL;DR: In this article , an implicit 3D morphable face model is trained from a collection of high-quality 3D scans, parameterized by geometry, expression, and texture latent codes with a learned SDF and explicit UV texture parameterization.
Journal ArticleDOI
Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks
TL;DR: Orientation Aware Vector Neuron Network (OAVNN) as mentioned in this paper is an extension of the vector neuron network that is robust to planar symmetric inputs, which is a rotation equivariant network.