首页/论文/2012.13118

arXiv 2012.131182020-12-24cs.CV

Hausdorff Point Convolution with Geometric Priors

Shenzhen University（深圳大学）；National University of Defense Technology（国防科技大学）；Tel Aviv University（特拉维夫大学）

Pengdi Huang, Liqiang Lin, Fuyou Xue, Kai Xu, Danny Cohen-Or, Hui Huang

备注：: 10 pages, 8 figures

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Without a shape-aware response, it is hard to characterize the 3D geometry of a point cloud efficiently with a compact set of kernels. In this paper, we advocate the use of Hausdorff distance as a shape-aware distance measure for calculating point convolutional responses. The technique we present, coined Hausdorff Point Convolution (HPC), is shape-aware. We show that HPC constitutes a powerful point feature learning with a rather compact set of only four types of geometric priors as kernels. We further develop a HPC-based deep neural network (HPC-DNN). Task-specific learning can be achieved by tuning the network weights for combining the shortest distances between input and kernel point sets. We also realize hierarchical feature learning by designing a multi-kernel HPC for multi-scale feature encoding. Extensive experiments demonstrate that HPC-DNN outperforms strong point convolution baselines (e.g., KPConv), achieving 2.8% mIoU performance boost on S3DIS and 1.5% on SemanticKITTI for semantic segmentation task.

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

A Convolution Tree with Deconvolution Branches: Exploiting Geometric Relationships for Single Shot Keypoint Detection

University of Maryland-College Park（马里兰大学帕克分校）

Recently, Deep Convolution Networks (DCNNs) have been applied to the task of face alignment and have shown potential for learning improved feature representations. Although deeper layers can capture abstract concepts like pose, it is difficult to capture the geometric relationships among the keypoints in DCNNs. In this paper, we propose a novel convolution-deconvolution network for facial keypoint detection. Our model predicts the 2D locations of the keypoints and their individual visibility along with 3D head pose, while exploiting the spatial relationships among different keypoints. Differen…

2017-04-06cs.CV

Beyond the Hausdorff Metric in Digital Topology

Department of Computer and Information Sciences, Niagara University（尼加拉瓜大学计算机与信息科学系）；Department of Computer Science and Engineering, State University of New York at Buffalo（纽约州立大学布法罗分校计算机科学与工程系）

Two objects may be close in the Hausdorff metric, yet have very different geometric and topological properties. We examine other methods of comparing digital images such that objects close in each of these measures have some similar geometric or topological property. Such measures may be combined with the Hausdorff metric to yield a metric in which close images are similar with respect to multiple properties.

2021-09-23cs.CGcs.CVmath.MG

Geometric Operator Convolutional Neural Network

USTC（中国科学技术大学）

The Convolutional Neural Network (CNN) has been successfully applied in many fields during recent decades; however it lacks the ability to utilize prior domain knowledge when dealing with many realistic problems. We present a framework called Geometric Operator Convolutional Neural Network (GO-CNN) that uses domain knowledge, wherein the kernel of the first convolutional layer is replaced with a kernel generated by a geometric operator function. This framework integrates many conventional geometric operators, which allows it to adapt to a diverse range of problems. Under certain conditions, we…

2018-09-04cs.CV

可操控卷积的几何方法

A Geometric Approach to Steerable Convolutions

Department of Statistics（统计学系）；University of Chicago（芝加哥大学）；Department of Computer Science（计算机科学系）

本文提出一种基于几何和模式匹配原理的可操控卷积神经网络新推导方法，并利用插值核构建卷积层，提升了对噪声数据的鲁棒性。

2025-10-24cs.CV

All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks

University of Pennsylvania（宾夕法尼亚大学）

Image feature matching is a fundamental part of many geometric computer vision applications, and using multiple images can improve performance. In this work, we formulate multi-image matching as a graph embedding problem then use a Graph Convolutional Network to learn an appropriate embedding function for aligning image features. We use cycle consistency to train our network in an unsupervised fashion, since ground truth correspondence is difficult or expensive to aquire. In addition, geometric consistency losses can be added at training time, even if the information is not available in the te…

2019-01-07cs.CV

Geometric Graph Representations and Geometric Graph Convolutions for Deep Learning on Three-Dimensional (3D) Graphs

IBM（国际商业机器公司）

The geometry of three-dimensional (3D) graphs, consisting of nodes and edges, plays a crucial role in many important applications. An excellent example is molecular graphs, whose geometry influences important properties of a molecule including its reactivity and biological activity. To facilitate the incorporation of geometry in deep learning on 3D graphs, we define three types of geometric graph representations: positional, angle-geometric and distance-geometric. For proof of concept, we use the distance-geometric graph representation for geometric graph convolutions. Further, to utilize stan…

2020-06-02cs.CVcs.LG

更多相关论文收起更多论文

GeoGCN: Geometric Dual-domain Graph Convolution Network for Point Cloud Denoising

Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Lingnan University（岭南大学）；Hong Kong Metropolitan University（香港都会大学）

We propose GeoGCN, a novel geometric dual-domain graph convolution network for point cloud denoising (PCD). Beyond the traditional wisdom of PCD, to fully exploit the geometric information of point clouds, we define two kinds of surface normals, one is called Real Normal (RN), and the other is Virtual Normal (VN). RN preserves the local details of noisy point clouds while VN avoids the global shape shrinkage during denoising. GeoGCN is a new PCD paradigm that, 1) first regresses point positions by spatialbased GCN with the help of VNs, 2) then estimates initial RNs by performing Principal Comp…

2022-10-28cs.CV

Distance-Geometric Graph Convolutional Network (DG-GCN) for Three-Dimensional (3D) Graphs

IBM（国际商业机器公司）

The distance-geometric graph representation adopts a unified scheme (distance) for representing the geometry of three-dimensional(3D) graphs. It is invariant to rotation and translation of the graph and it reflects pair-wise node interactions and their generally local nature. To facilitate the incorporation of geometry in deep learning on 3D graphs, we propose a message-passing graph convolutional network based on the distance-geometric graph representation: DG-GCN (distance-geometric graph convolution network). It utilizes continuous-filter convolutional layers, with filter-generating network…

2021-03-22cs.CVcs.LG

2D-3D Geometric Fusion Network using Multi-Neighbourhood Graph Convolution for RGB-D Indoor Scene Classification

Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）

Multi-modal fusion has been proved to help enhance the performance of scene classification tasks. This paper presents a 2D-3D Fusion stage that combines 3D Geometric Features with 2D Texture Features obtained by 2D Convolutional Neural Networks. To get a robust 3D Geometric embedding, a network that uses two novel layers is proposed. The first layer, Multi-Neighbourhood Graph Convolution, aims to learn a more robust geometric descriptor of the scene combining two different neighbourhoods: one in the Euclidean space and the other in the Feature space. The second proposed layer, Nearest Voxel Po…

2021-05-27cs.AIcs.CV

Fully Convolutional Geometric Features for Category-level Object Alignment

University of California, San Diego（加利福尼亚大学圣迭戈分校）

This paper focuses on pose registration of different object instances from the same category. This is required in online object mapping because object instances detected at test time usually differ from the training instances. Our approach transforms instances of the same category to a normalized canonical coordinate frame and uses metric learning to train fully convolutional geometric features. The resulting model is able to generate pairs of matching points between the instances, allowing category-level registration. Evaluation on both synthetic and real-world data shows that our method prov…

2021-03-08cs.CVcs.RO

Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs

Qualcomm AI Research（高通AI研究院）；Qualcomm Technologies, Inc.（高通技术公司）；University of Amsterdam（阿姆斯特丹大学）

A common approach to define convolutions on meshes is to interpret them as a graph and apply graph convolutional networks (GCNs). Such GCNs utilize isotropic kernels and are therefore insensitive to the relative orientation of vertices and thus to the geometry of the mesh as a whole. We propose Gauge Equivariant Mesh CNNs which generalize GCNs to apply anisotropic gauge equivariant kernels. Since the resulting features carry orientation information, we introduce a geometric message passing scheme defined by parallel transporting features over mesh edges. Our experiments validate the significan…

2021-11-19cs.CVcs.LGstat.ML

重访用于目标6D位姿估计的全卷积几何特征

Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation

Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）

针对现有6D目标位姿估计忽略点级判别特征学习的问题，研究重访并适配FCGF，通过损失、输入表示、训练策略等修改及适配的数据增强，在主流基准上超越同类方法，还开展消融实验验证各修改的贡献。

2023-10-03cs.AIcs.CV

Prediction of Geometric Transformation on Cardiac MRI via Convolutional Neural Network

DongHua University（东华大学）

In the field of medical image, deep convolutional neural networks(ConvNets) have achieved great success in the classification, segmentation, and registration tasks thanks to their unparalleled capacity to learn image features. However, these tasks often require large amounts of manually annotated data and are labor-intensive. Therefore, it is of significant importance for us to study unsupervised semantic feature learning tasks. In our work, we propose to learn features in medical images by training ConvNets to recognize the geometric transformation applied to images and present a simple self-…

2022-11-12cs.CVcs.LGeess.IV