Robust Watertight Manifold Surface Generation Method for ShapeNet Models
arXiv:1802.01698
Abstract
In this paper, we describe a robust algorithm for 2-Manifold generation of various kinds of ShapeNet Models. The input of our pipeline is a triangle mesh, with a set of vertices and triangular faces. The output of our pipeline is a 2-Manifold with vertices roughly uniformly distributed on the geometry surface. Our algorithm uses an octree to represent the original mesh, and construct the surface by isosurface extraction. Finally, we project the vertices to the original mesh to achieve high precision. As a result, our method can be adopted efficiently to all ShapeNet models with the guarantee of correct 2-Manifold topology.
arXiv commentAlgorithm for generating manifolds of ShapeNet Models
Cited by in corpus (24)
- Subdivision-Based Mesh Convolution Networks
- Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search
- Deep Level Sets: Implicit Surface Representations for 3D Shape Inference
- PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models
- SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform
- CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects
- Deep Learning for Real-Time Aerodynamic Evaluations of Arbitrary Vehicle Shapes
- SDM-NET: Deep Generative Network for Structured Deformable Mesh
- ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soups
- Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
- DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces
- LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
- Adversarial Texture Optimization from RGB-D Scans
- Shape from Projections via Differentiable Forward Projector for Computed Tomography
- IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning
- Efficient and Accurate Candidate Generation for Grasp Pose Detection in SE(3)
- Shape As Points: A Differentiable Poisson Solver
- Learning Manifold Patch-Based Representations of Man-Made Shapes
- Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
- Point2Skeleton: Learning Skeletal Representations from Point Clouds
- LASR: Learning Articulated Shape Reconstruction from a Monocular Video
- MeshODE: A Robust and Scalable Framework for Mesh Deformation
- DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates
- Deep Hybrid Self-Prior for Full 3D Mesh Generation