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
Category-Level Articulated Object Pose Estimation
TL;DR: In this article, a canonical representation for different articulated objects in a given category is proposed, which constructs a canonical object space as well as a set of canonical part spaces, and each canonical part space further normalizes its part pose and scale.
Journal ArticleDOI
EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision
TL;DR: In this paper , the authors introduce equivariant shape representations to segment objects in 3D scenes without annotations or training on scenes, and propose an unsupervised segmentation method by exploiting single object shape priors.
Journal ArticleDOI
SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates
TL;DR: In this article , the authors propose a new method that learns to predict, for each view, a continuous, multimodal distribution of depth estimates using conditional Implicit Maximum Likelihood Estimation (cIMLE).
Posted Content
Joint Learning of 3D Shape Retrieval and Deformation
Mikaela Angelina Uy,Vladimir G. Kim,Minhyuk Sung,Noam Aigerman,Siddhartha Chaudhuri,Leonidas J. Guibas +5 more
TL;DR: In this paper, a joint learning procedure that simultaneously trains the neural deformation module along with the embedding space used by the retrieval module is proposed, which enables the network to learn a deformation-aware embedding, so that retrieved models are more amenable to match the target after an appropriate deformation.
Posted Content
Stable Delaunay Graphs
TL;DR: It is shown that if an edge is stable in the Euclidean Delaunay triangulation of P, then it is also a stable edge, though for a different value of $$\alpha $$α, in the Delaunays triangulations of P under any convex distance function that is sufficiently close to the Euclidan norm, and vice-versa.