Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
arXiv:2007.10973
Abstract
Meshes are important representations of physical 3D entities in the virtual world. Applications like rendering, simulations and 3D printing require meshes to be manifold so that they can interact with the world like the real objects they represent. Prior methods generate meshes with great geometric accuracy but poor manifoldness. In this work, we propose Neural Mesh Flow (NMF) to generate two-manifold meshes for genus-0 shapes. Specifically, NMF is a shape auto-encoder consisting of several Neural Ordinary Differential Equation (NODE)[1] blocks that learn accurate mesh geometry by progressively deforming a spherical mesh. Training NMF is simpler compared to state-of-the-art methods since it does not require any explicit mesh-based regularization. Our experiments demonstrate that NMF facilitates several applications such as single-view mesh reconstruction, global shape parameterization, texture mapping, shape deformation and correspondence. Importantly, we demonstrate that manifold meshes generated using NMF are better-suited for physically-based rendering and simulation. Code and data are released.
arXiv commentProject Page: https://kunalmgupta.github.io/projects/NeuralMeshflow.html
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Open3D: A Modern Library for 3D Data Processing
- MeshCNN: A Network with an Edge
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
- Neural Ordinary Differential Equations
- Dissecting Neural ODEs
- Learning to Reconstruct Shapes from Unseen Classes
- Robust Watertight Manifold Surface Generation Method for ShapeNet Models
- Deep Level Sets: Implicit Surface Representations for 3D Shape Inference
- On Robustness of Neural Ordinary Differential Equations
- GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects