Timezone: »

 
Poster
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Edward Smith · Scott Fujimoto · Adriana Romero Soriano · David Meger

Tue Jun 11 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #145
in Posters Tue »

Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined graph through a series of graph convolutions, leading to compromises with respect to performance or resolution. In this paper, we argue that the graph representation of geometric objects allows for additional structure, which should be leveraged for enhanced reconstruction. Thus, we propose a system which properly benefits from the advantages of the geometric structure of graph-encoded objects by introducing (1) a graph convolutional update preserving vertex information; (2) an adaptive splitting heuristic allowing detail to emerge; and (3) a training objective operating both on the local surfaces defined by vertices as well as the global structure defined by the mesh. Our proposed method is evaluated on the task of 3D object reconstruction from images with the ShapeNet dataset, where we demonstrate state of the art performance, both visually and numerically, while having far smaller space requirements by generating adaptive meshes.

Keywords: Algorithms · Computer Vision · Deep Learning Theory

Author Information

Edward Smith (McGill University)
Scott Fujimoto (McGill University)
Adriana Romero Soriano (FAIR)
David Meger (McGill University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors