BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:StructureNet: Hierarchical Graph Networks for 3D Shape Generation 
 - Professor Niloy Mitra - Professor of Geometry Processing in the Departme
 nt of Computer Science\, University College London (UCL)
DTSTART:20191030T150500Z
DTEND:20191030T155500Z
UID:TALK131914@talks.cam.ac.uk
CONTACT:jo de bono
DESCRIPTION:The ability to generate novel\, diverse\, and realistic 3D sha
 pes along with associated part semantics and structure is central to many 
 applications requiring high-quality 3D assets or large volumes of realisti
 c training data. A key challenge towards this goal is how to accommodate d
 iverse shape\, including both continuous deformations of parts as well as 
 structural or discrete alterations which add to\, remove from\, or modify 
 the shape constituents and compositional structure. Such object structure 
 can typically be organized into a hierarchy of constituent object parts an
 d relationships\, represented as a hierarchy of n-ary graphs. We introduce
  StructureNet\, a hierarchical graph network which (i) can directly encode
  shapes represented as such n-ary graphs\; (ii) can be robustly trained on
  large and complex shape families\; and (iii) be used to generate a great 
 diversity of realistic structured shape geometries. Technically\, we accom
 plish this by drawing inspiration from recent advances in graph neural net
 works to propose an order-invariant encoding of n-ary graphs\, considering
  jointly both part geometry and inter-part relations during network traini
 ng. We extensively evaluate the quality of the learned latent spaces for v
 arious shape families and show significant advantages over baseline and co
 mpeting methods. The learned latent spaces enable several structure-aware 
 geometry processing applications\, including shape generation and interpol
 ation\, shape editing\, or shape structure discovery directly from un-anno
 tated images\, point clouds\, or partial scans. For more details\, please 
 visit http://geometry.cs.ucl.ac.uk/projects/2019/structurenet/.
LOCATION:Lecture Theatre 2\, Computer Laboratory
END:VEVENT
END:VCALENDAR