Deep Surface Reconstruction from Point Clouds with Visibility Information
This work addresses a limitation in neural surface reconstruction methods for 3D computer vision applications, though it appears incremental.
The paper tackles surface reconstruction from point clouds by incorporating sensor visibility information, which improves both reconstruction accuracy and generalization to unseen shapes.
Most current neural networks for reconstructing surfaces from point clouds ignore sensor poses and only operate on raw point locations. Sensor visibility, however, holds meaningful information regarding space occupancy and surface orientation. In this paper, we present two simple ways to augment raw point clouds with visibility information, so it can directly be leveraged by surface reconstruction networks with minimal adaptation. Our proposed modifications consistently improve the accuracy of generated surfaces as well as the generalization ability of the networks to unseen shape domains. Our code and data is available at https://github.com/raphaelsulzer/dsrv-data.