Vladimir G. Kim
Finding Structure in Large Collections of 3D Models
As large repositories of 3D shape collections grow, understanding the geometric data, especially encoding the inter-model similarity, their variations, semantics and functionality, is of central importance. My research addresses the challenge of deriving probabilistic models that capture common structure in large, unorganized, and diverse collections of 3D polygonal shapes. In my talk I will present several such models and their applications. I will cover basic tools for establishing relationships between models in highly heterogeneous datasets: correspondences, consistent segmentation, part hierarchies, and human-centric analysis. I will demonstrate how these analysis results can be used to learn a structural prior that can be used for organizing big shape repositories, reconstructing accurate and complete geometry from partial RGB-D scans.
Vladimir is a Research Scientist at Adobe’s Creative Technologies Lab. Prior to that, he was a postdoctoral scholar at Stanford University, and he obtained his Ph.D. from Princeton University. Vladimir’s research interests include geometry analysis, computer graphics, and computer vision. His is developing algorithms to analyze large repositories of 3D models to infer structural, semantic, and functional attributes of objects and environments from their three-dimensional geometry.