首页/论文/1908.02507

arXiv 1908.025072019-08-07cs.GRcs.CVcs.LGeess.IV

Mesh Variational Autoencoders with Edge Contraction Pooling

Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Cardiff University（卡迪夫大学）；City University of Hong Kong（香港城市大学）

Yu-Jie Yuan, Yu-Kun Lai, Jie Yang, Hongbo Fu, Lin Gao

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

3D shape analysis is an important research topic in computer vision and graphics. While existing methods have generalized image-based deep learning to meshes using graph-based convolutions, the lack of an effective pooling operation restricts the learning capability of their networks. In this paper, we propose a novel pooling operation for mesh datasets with the same connectivity but different geometry, by building a mesh hierarchy using mesh simplification. For this purpose, we develop a modified mesh simplification method to avoid generating highly irregularly sized triangles. Our pooling operation effectively encodes the correspondence between coarser and finer meshes in the hierarchy. We then present a variational auto-encoder structure with the edge contraction pooling and graph-based convolutions, to explore probability latent spaces of 3D surfaces. Our network requires far fewer parameters than the original mesh VAE and thus can handle denser models thanks to our new pooling operation and convolutional kernels. Our evaluation also shows that our method has better generalization ability and is more reliable in various applications, including shape generation, shape interpolation and shape embedding.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

面向基准的3D解剖形状分类

Benchmark-Ready 3D Anatomical Shape Classification

Brno University of Technology, Brno, Czech Republic（布拉格技术大学）

针对解剖3D形状分类中网格数据复杂和缺乏标准化基准的问题，提出不可学习的PSPooling算子并结合自监督图自编码器，在MedShapeNet19基准上显著提升了低标签场景下的重建保真度与分类准确率。

2025-11-03cs.CV

MeshConv3D：面向三角形3D网格的高效卷积与池化算子

MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes

Keyrus（凯鲁斯公司）；Telecom SudParis（巴黎高等电信学院）；Institut Polytechnique de Paris（巴黎综合理工学院）

针对3D网格的不规则连接问题，本文提出MeshConv3D，通过专用卷积与基于面坍缩的池化直接处理任意拓扑网格，并在三个基准上以更低内存和计算量取得相当或更优分类性能。

2025-01-07cs.CVcs.GR

LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling

Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Cardiff University（卡迪夫大学）

3D models are commonly used in computer vision and graphics. With the wider availability of mesh data, an efficient and intrinsic deep learning approach to processing 3D meshes is in great need. Unlike images, 3D meshes have irregular connectivity, requiring careful design to capture relations in the data. To utilize the topology information while staying robust under different triangulation, we propose to encode mesh connectivity using Laplacian spectral analysis, along with Mesh Pooling Blocks (MPBs) that can split the surface domain into local pooling patches and aggregate global informatio…

2019-10-30cs.CVcs.GR

基于网格潜在扩散模型的3D心脏解剖结构生成

3D Cardiac Anatomy Generation Using Mesh Latent Diffusion Models

Department of Computer Science, University of Oxford（计算机科学系，牛津大学）；Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford（生物医学工程研究所，工程科学系，牛津大学）；Visual Geometry Group, Department of Engineering Science, University of Oxford（视觉几何组，工程科学系，牛津大学）；Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford（心血管医学部，拉德克利夫医学系，牛津大学）

针对3D医学成像中心脏解剖结构生成的需求，本研究提出MeshLDM架构，将潜在扩散模型应用于左心室3D网格生成，成功捕捉心脏舒张与收缩期形态特征，生成网格与金标准群体均值差异仅2.4%。

2025-08-18cs.CVcs.LGeess.IV

MeshCNN: A Network with an Edge

Tel Aviv University（特拉维夫大学）；Amazon（亚马逊）

Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This non-uniformity and irregularity, however, inhibits mesh analysis efforts using neural networks that combine convolution and pooling operations. In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes. Analogous to classic CNNs, MeshCNN combine…

2019-02-13cs.CVcs.GRcs.LG

TetGAN: A Convolutional Neural Network for Tetrahedral Mesh Generation

University of Chicago（芝加哥大学）；Tel Aviv University（特拉维夫大学）；Purdue University（普渡大学）

We present TetGAN, a convolutional neural network designed to generate tetrahedral meshes. We represent shapes using an irregular tetrahedral grid which encodes an occupancy and displacement field. Our formulation enables defining tetrahedral convolution, pooling, and upsampling operations to synthesize explicit mesh connectivity with variable topological genus. The proposed neural network layers learn deep features over each tetrahedron and learn to extract patterns within spatial regions across multiple scales. We illustrate the capabilities of our technique to encode tetrahedral meshes into…

2022-10-11cs.CVcs.GRcs.LG

更多相关论文收起更多论文

DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling

Ben-Gurion University of the Negev（内盖夫本-古里安大学）

Graph Convolutional Networks (GCNs) have shown to be effective in handling unordered data like point clouds and meshes. In this work we propose novel approaches for graph convolution, pooling and unpooling, inspired from finite differences and algebraic multigrid frameworks. We form a parameterized convolution kernel based on discretized differential operators, leveraging the graph mass, gradient and Laplacian. This way, the parameterization does not depend on the graph structure, only on the meaning of the network convolutions as differential operators. To allow hierarchical representations o…

2020-10-22cs.CVcs.GRcs.LG

Subdivision-Based Mesh Convolution Networks

Tsinghua University（清华大学）；Cardiff University（卡迪夫大学）

Convolutional neural networks (CNNs) have made great breakthroughs in 2D computer vision. However, their irregular structure makes it hard to harness the potential of CNNs directly on meshes. A subdivision surface provides a hierarchical multi-resolution structure, in which each face in a closed 2-manifold triangle mesh is exactly adjacent to three faces. Motivated by these two observations, this paper presents SubdivNet, an innovative and versatile CNN framework for 3D triangle meshes with Loop subdivision sequence connectivity. Making an analogy between mesh faces and pixels in a 2D image al…

2021-12-29cs.CVcs.GRcs.LG

Laplacian2Mesh: Laplacian-Based Mesh Understanding

Shandong University（山东大学）；Qingdao University of Science and Technology（青岛科技大学）；Zhejiang University（浙江大学）

Geometric deep learning has sparked a rising interest in computer graphics to perform shape understanding tasks, such as shape classification and semantic segmentation. When the input is a polygonal surface, one has to suffer from the irregular mesh structure. Motivated by the geometric spectral theory, we introduce Laplacian2Mesh, a novel and flexible convolutional neural network (CNN) framework for coping with irregular triangle meshes (vertices may have any valence). By mapping the input mesh surface to the multi-dimensional Laplacian-Beltrami space, Laplacian2Mesh enables one to perform sh…

2023-03-16cs.CVcs.GRcs.LG

面向网格分类与语义部件分割的任务驱动网络

A Task-driven Network for Mesh Classification and Semantic Part Segmentation

Shandong University（山东大学）；Nankai University（南开大学）；Qingdao University of Science and Technology（青岛科技大学）

本文提出Mesh-MLP，一种仅基于多层感知器的简单端到端网络，用于网格分类与语义部件分割，通过热核签名和二面角输入及层归一化，验证了全MLP架构的有效性。

2023-12-28cs.CVcs.GR

Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

South China University of Technology（华南理工大学）；University of California at Berkeley（加州大学伯克利分校）

Reconstruction of object or scene surfaces has tremendous applications in computer vision, computer graphics, and robotics. In this paper, we study a fundamental problem in this context about recovering a surface mesh from an implicit field function whose zero-level set captures the underlying surface. To achieve the goal, existing methods rely on traditional meshing algorithms; while promising, they suffer from loss of precision learned in the implicit surface networks, due to the use of discrete space sampling in marching cubes. Given that an MLP with activations of Rectified Linear Unit (Re…

2021-06-18cs.CVcs.GR