University of Cambridge > Talks.cam > Wednesday Seminars - Department of Computer Science and Technology  > StructureNet: Hierarchical Graph Networks for 3D Shape Generation

StructureNet: Hierarchical Graph Networks for 3D Shape Generation

Add to your list(s) Download to your calendar using vCal

  • UserProfessor Niloy Mitra - Professor of Geometry Processing in the Department of Computer Science, University College London (UCL)
  • ClockWednesday 30 October 2019, 15:05-15:55
  • HouseLecture Theatre 2, Computer Laboratory.

If you have a question about this talk, please contact jo de bono.

The ability to generate novel, diverse, and realistic 3D shapes along with associated part semantics and structure is central to many applications requiring high-quality 3D assets or large volumes of realistic training data. A key challenge towards this goal is how to accommodate diverse 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 and 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 accomplish this by drawing inspiration from recent advances in graph neural networks to propose an order-invariant encoding of n-ary graphs, considering jointly both part geometry and inter-part relations during network training. We extensively evaluate the quality of the learned latent spaces for various shape families and show significant advantages over baseline and competing methods. The learned latent spaces enable several structure-aware geometry processing applications, including shape generation and interpolation, shape editing, or shape structure discovery directly from un-annotated images, point clouds, or partial scans. For more details, please visit http://geometry.cs.ucl.ac.uk/projects/2019/structurenet/.

This talk is part of the Wednesday Seminars - Department of Computer Science and Technology series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity