GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
This work addresses mesh reconstruction for 3D objects, offering improvements in performance and efficiency, though it appears incremental as it builds on existing graph-based approaches.
The paper tackles the problem of 3D object reconstruction from images by proposing a method that leverages geometric structure in graph-encoded meshes, resulting in state-of-the-art performance with smaller space requirements on the ShapeNet dataset.
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