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
Proceedings ArticleDOI
Taskonomy: Disentangling Task Transfer Learning
Amir Roshan Zamir,Alexander Sax,William B. Shen,Leonidas J. Guibas,Jitendra Malik,Silvio Savarese +5 more
TL;DR: In this article, the authors propose a taxonomic map for task transfer learning, which is a set of tools for computing and probing this taxonomical structure including a solver to find supervision policies for their use cases.
Journal ArticleDOI
A scalable active framework for region annotation in 3D shape collections
Li Yi,Vladimir G. Kim,Duygu Ceylan,I-Chao Shen,Mengyan Yan,Hao Su,Cewu Lu,Qixing Huang,Alla Sheffer,Leonidas J. Guibas +9 more
TL;DR: This work proposes a novel active learning method capable of enriching massive geometric datasets with accurate semantic region annotations, and demonstrates that incorporating verification of all produced labelings within this unified objective improves both accuracy and efficiency of the active learning procedure.
Journal ArticleDOI
Shape google: Geometric words and expressions for invariant shape retrieval
TL;DR: This article uses multiscale diffusion heat kernels as “geometric words” to construct compact and informative shape descriptors by means of the “bag of features” approach, and shows that shapes can be efficiently represented as binary codes.
Book
Robust Monte Carlo methods for light transport simulation
Leonidas J. Guibas,Eric Veach +1 more
TL;DR: This dissertation develops new Monte Carlo techniques that greatly extend the range of input models for which light transport simulations are practical, and shows how light transport can be formulated as an integral over a space of paths.
Proceedings ArticleDOI
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
TL;DR: A scalable and overfit-resistant image synthesis pipeline, together with a novel CNN specifically tailored for the viewpoint estimation task, is proposed that can significantly outperform state-of-the-art methods on PASCAL 3D+ benchmark.