Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance

Abstract

We are interested in reconstructing the mesh representation of object surfaces from point clouds. Surface reconstruction is a prerequisite for downstream applications such as rendering, collision avoidance for planning, animation, etc. However, the task is challenging if the input point cloud has a low resolution, which is common in real-world scenarios (e.g., from LiDAR or Kinect sensors). Existing learning-based mesh generative methods mostly predict the surface by first building a shape embedding that is at the whole object level, a design that causes issues in generating fine-grained details and generalizing to unseen categories. Instead, we propose to leverage the input point cloud as much as possible, by only adding connectivity information to existing points. Particularly, we predict which triplets of points should form faces. Our key innovation is a surrogate of local connectivity, calculated by comparing the intrinsic/extrinsic metrics. We learn to predict this surrogate using a deep point cloud network and then feed it to an efficient postprocessing module for high-quality mesh generation. We demonstrate that our method can not only preserve details, handle ambiguous structures, but also possess strong generalizability to unseen categories by experiments on synthetic and real data.

Learning Delaunay Surface Elements for Mesh Reconstruction

“…However, this technique processes triangles independently and only promotes watertight and manifold structure through soft penalties. The second method was presented in [33], and estimates local connectivity by predicting the ratio between geodesic and Euclidean distances. This is a powerful signal, which is then fed into a non-learning based selection procedure, which aims to finally output a coherent mesh.…”

“…In contrast to both of these approaches [41,33], we formulate the meshing problem as learning of (local) Delaunay triangulations. Starting from the restricted Voronoi diagram based formulation proposed in [10] we use data-driven priors to directly learn local projections to create local Delaunay patches.…”

“…And triangles that appear only once are considered least likely. Finally, we use the triangle selection process proposed in [33] to produce a…”

“…PointTriNet [41] and IER meshing [33] We compare our method to two recent learning based methods for triangulating point clouds. We retrain PointTriNet on our dataset.…”

“…Most of such techniques focus on robustly predicting a signed distance field or simply an occupancy map, from which a mesh is subsequently extracted using volumetric triangulation [12,22,39]. Only two recent methods [41,33] produce a triangulation while respecting the original point set, but they ignore the quality of the triangles or have trouble reconstructing sharp features.…”