Overview
The Computational Vision and Geometry Lab (CVGL) at Stanford is directed by Prof. Silvio Savarese. Our research addresses the theoretical foundations and practical applications of computational vision. Our interest lies in discovering and proposing the fundamental principles, algorithms and implementations for solving high level visual recognition and reconstruction problems such as object and scene understanding as well as human behavior recognition in the complex 3D world.
Photo Gallery
Here are some highlights from our featured projects:
2D-3D-S
Joint 2D-3D-Semantic Data for Indoor Scene Understanding
FBN
Feedback Networks
UCN
Univeral Correspondence Network
R2N2
3D-R2N2
Recurrent Reconstruction Neural Network
Generic 3D Representation
Generic 3D Representation
Lifted Struct
Deep Metric Learning via Lifted Structured Feature Embedding
Building Parser
3D Semantic Parsing of Large-Scale Indoor Spaces
3DVP
3D Voxel Patterns for Object Category Recognition
Contacts
Address
Computer Science Department, Stanford University
353 Serra Mall, Stanford, CA 94305-9025.
Admin: Tin Tin Wisniewski
Email: tintinyw at cs dot stanford dot edu, Phone: (650) 723-3819, Fax: (650) 725-1449