GAMesh: Guided and Augmented Meshing for Deep Point Networks
This addresses surface reconstruction challenges in computer vision and graphics, particularly for applications like 3D shape prediction, but it is incremental as it builds on existing meshing and point network techniques.
The paper tackles the problem of generating surfaces from point networks by introducing GAMesh, which uses a mesh prior to ensure consistent topology while controlling geometric fidelity, making it independent of point density and distribution issues common in traditional methods. The result is a method that improves single-view shape prediction, enables fair evaluation of point networks, and allows training networks to produce adaptive meshes with arbitrary topologies.
We present a new meshing algorithm called guided and augmented meshing, GAMesh, which uses a mesh prior to generate a surface for the output points of a point network. By projecting the output points onto this prior and simplifying the resulting mesh, GAMesh ensures a surface with the same topology as the mesh prior but whose geometric fidelity is controlled by the point network. This makes GAMesh independent of both the density and distribution of the output points, a common artifact in traditional surface reconstruction algorithms. We show that such a separation of geometry from topology can have several advantages especially in single-view shape prediction, fair evaluation of point networks and reconstructing surfaces for networks which output sparse point clouds. We further show that by training point networks with GAMesh, we can directly optimize the vertex positions to generate adaptive meshes with arbitrary topologies.