DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction

by   Yiming Luo, et al.

In this paper, a novel learning-based network, named DeepDT, is proposed to reconstruct the surface from Delaunay triangulation of point cloud. DeepDT learns to predict inside/outside labels of Delaunay tetrahedrons directly from a point cloud and corresponding Delaunay triangulation. The local geometry features are first extracted from the input point cloud and aggregated into a graph deriving from the Delaunay triangulation. Then a graph filtering is applied on the aggregated features in order to add structural regularization to the label prediction of tetrahedrons. Due to the complicated spatial relations between tetrahedrons and the triangles, it is impossible to directly generate ground truth labels of tetrahedrons from ground truth surface. Therefore, we propose a multilabel supervision strategy which votes for the label of a tetrahedron with labels of sampling locations inside it. The proposed DeepDT can maintain abundant geometry details without generating overly complex surfaces , especially for inner surfaces of open scenes. Meanwhile, the generalization ability and time consumption of the proposed method is acceptable and competitive compared with the state-of-the-art methods. Experiments demonstrate the superior performance of the proposed DeepDT.


page 6

page 7


TSRNet: Scalable 3D Surface Reconstruction Network for Point Clouds using Tangent Convolution

Existing learning-based surface reconstruction methods from point clouds...

Evaluate Geometry of Radiance Field with Low-frequency Color Prior

Radiance field is an effective representation of 3D scenes, which has be...

Critical Regularizations for Neural Surface Reconstruction in the Wild

Neural implicit functions have recently shown promising results on surfa...

IterativePFN: True Iterative Point Cloud Filtering

The quality of point clouds is often limited by noise introduced during ...

Improving the quality of dental crown using a Transformer-based method

Designing a synthetic crown is a time-consuming, inconsistent, and labor...

Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Surface reconstruction from point clouds is vital for 3D computer vision...

RFEPS: Reconstructing Feature-line Equipped Polygonal Surface

Feature lines are important geometric cues in characterizing the structu...

Please sign up or login with your details

Forgot password? Click here to reset