MeshCNN: a network with an edge
Explore this paper's citation graph
Summary
This paper utilizes the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes, and demonstrates the effectiveness of MeshCNN on various learning tasks applied to 3D meshes.
- Type
- article
- Published
- 2019-07-12
- Cited by
- 382
- References
- 81
- Access
- Open access
- OpenAlex
- https://openalex.org/W2891396148
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:52286469
Keywords
Polygon mesh, Pooling, Computer science, Geodesic, Leverage (statistics)
References
- Deep Convolutional Networks on Graph-Structured Data
- Multi-view Convolutional Neural Networks for 3D Shape Recognition
- Spectral Networks and Locally Connected Networks on Graphs
- Rectified Linear Units Improve Restricted Boltzmann Machines
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Polygon Mesh Processing
- Learning class‐specific descriptors for deformable shapes using localized spectral convolutional networks
- FAUST: Dataset and Evaluation for 3D Mesh Registration
- SCAPE: shape completion and animation of people
- Shape Similarity Measure Based on Correspondence of Visual Parts
- Active co-analysis of a set of shapes
- New quadric metric for simplifying meshes with appearance attributes
- Shape google: Geometric words and expressions for invariant shape retrieval
- View-dependent refinement of progressive meshes
- Intrinsic shape context descriptors for deformable shapes
- Practical quad mesh simplification
- SHape REtrieval Contest 2007: Watertight Models Track
- Learning 3D mesh segmentation and labeling
- QSplat: a multiresolution point rendering system for large meshes
- Articulated mesh animation from multi-view silhouettes
Cited by
- Learning Generative Models of 3D Structures
- Higher-Order Function Networks for Learning Composable 3D Object Representations
- StructureNet
- Mesh Variational Autoencoders with Edge Contraction Pooling
- SDM-NET
- Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
- Applications and Challenges of Machine Learning to Enable Realistic Cellular Simulations
- MGCN
- FEA-Net: A Physics-guided Data-driven Model for Efficient Mechanical Response Prediction
- IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning
- PolySquare: a search engine for 3D models with tag propagation
- PointGMM: A Neural GMM Network for Point Clouds
- Neural subdivision
- A full migration BBO algorithm with enhanced population quality bounds for multimodal biomedical image registration
- Skeleton-aware networks for deep motion retargeting
- DiscretizationNet: A Machine-Learning based solver for Navier-Stokes Equations using Finite Volume Discretization
- Self-organizing network modelling of 3D objects
- ZerNet: Convolutional Neural Networks on Arbitrary Surfaces Via Zernike Local Tangent Space Estimation
- Deep Learning Techniques for Community Detection in Social Networks
- Point2Mesh