Deep Surface Reconstruction from Point Clouds with Visibility Information
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.
Code (1)
Tasks
Surface ReconstructionSimilar Papers 제목 키워드 기반
Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
We introduce a novel learning-based, visibility-aware, surface reconstruction method for large-scale, defect-laden point clouds. Our approach can cope with the scale and variety of point cloud defects encountered in real…
Graph Neural NetworkSurface ReconstructionVis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility
We present a novel framework for mesh reconstruction from unstructured point clouds by taking advantage of the learned visibility of the 3D points in the virtual views and traditional graph-cut based mesh generation. Spe…
3D Surface GenerationBinary ClassificationDepth CompletionVisibility Estimation from Point CloudNeural Visibility of Point Sets
Point clouds are widely used representations of 3D data, but determining the visibility of points from a given viewpoint remains a challenging problem due to their sparse nature and lack of explicit connectivity. Traditi…
Computational EfficiencyBinary ClassificationPoint CloudsOut-of-Core Surface Reconstruction via Global $TGV$ Minimization
We present an out-of-core variational approach for surface reconstruction from a set of aligned depth maps. Input depth maps are supposed to be reconstructed from regular photos or/and can be a representation of terrestr…
DiversityGPUSurface ReconstructionOut-of-Core Surface Reconstruction via Global TGV Minimization
We present an out-of-core variational approach for surface reconstruction from a set of aligned depth maps. Input depth maps are supposed to be reconstructed from regular photos or/and can be a representation of terr…
DiversityGPUSurface Reconstruction