PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds

• URL: http://arxiv.org/abs/2111.14067v1
• Date: Sun, 28 Nov 2021 07:26:55 GMT
• Title: PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds
• Authors: Jie Wang, Jianan Li, Lihe Ding, Ying Wang, Tingfa Xu
• Abstract summary: PaPooling explicitly models spatial relations among local points using a novel graph representation. It aggregates features in a position adaptive manner, enabling position-sensitive representation of aggregated features. It can significantly improve predictive accuracy, while with minimal extra computational overhead.
• Score: 15.878533142927102
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds. Nevertheless, existing preeminent point cloud backbones usually incorporate max/average pooling for local feature aggregation, which largely ignores points' positional distribution, leading to inadequate assembling of fine-grained structures. To mitigate this bottleneck, we present an efficient alternative to max pooling, Position Adaptive Pooling (PAPooling), that explicitly models spatial relations among local points using a novel graph representation, and aggregates features in a position adaptive manner, enabling position-sensitive representation of aggregated features. Specifically, PAPooling consists of two key steps, Graph Construction and Feature Aggregation, respectively in charge of constructing a graph with edges linking the center point with every neighboring point in a local region to map their relative positional information to channel-wise attentive weights, and adaptively aggregating local point features based on the generated weights through Graph Convolution Network (GCN). PAPooling is simple yet effective, and flexible enough to be ready to use for different popular backbones like PointNet++ and DGCNN, as a plug-andplay operator. Extensive experiments on various tasks ranging from 3D shape classification, part segmentation to scene segmentation well demonstrate that PAPooling can significantly improve predictive accuracy, while with minimal extra computational overhead. Code will be released.

Related papers

• LoGDesc: Local geometric features aggregation for robust point cloud registration [4.888434990566421]
  This paper introduces a new hybrid descriptor for 3D point matching and point cloud registration. It combines local geometrical properties and learning-based feature propagation for each point's neighborhood structure description.
  arXiv  Detail & Related papers  (2024-10-03T12:11:22Z)
• Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis [59.12922158979068]
  Recently-based methods have shown strong performance in point cloud analysis. Simple architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. We propose Point Deformable Network (PDNet) to capture long-range relations with strong representation ability.
  arXiv  Detail & Related papers  (2023-12-20T14:52:07Z)
• Decoupled Local Aggregation for Point Cloud Learning [12.810517967372043]
  We propose to decouple the explicit modelling of spatial relations from local aggregation. We present DeLA, a lightweight point network, where in each learning stage relative spatial encodings are first formed. DeLA achieves over 90% overall accuracy on ScanObjectNN and 74% mIoU on S3DIS Area 5.
  arXiv  Detail & Related papers  (2023-08-31T08:21:29Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis [118.30840667784206]
  Key issue for point cloud data processing is extracting useful information from local regions. Previous works ignore the relation between edges in local regions, which encodes the local shape information. This paper proposes a novel Adaptive Edge-to-Edge Interaction Learning module.
  arXiv  Detail & Related papers  (2022-11-20T07:10:14Z)
• APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification [48.230170172837084]
  Point-cloud-based 3D classification task involves aggregating features from neighbor points. To address these issues, we propose a new local aggregator of linear complexity, coined as APP. We use an online normal estimation module to provide the explainable geometric information to enhance our APP modeling capability.
  arXiv  Detail & Related papers  (2022-05-02T12:21:11Z)
• SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space [50.14426188851305]
  We propose the first SE(3)-equivariant coordinate-based network for learning occupancy fields from point clouds. In contrast to previous shape reconstruction methods that align the input to a regular grid, we operate directly on the irregular, unoriented point cloud. We show that our method outperforms previous SO(3)-equivariant methods, as well as non-equivariant methods trained on SO(3)-augmented datasets.
  arXiv  Detail & Related papers  (2022-04-05T17:59:15Z)
• ODFNet: Using orientation distribution functions to characterize 3D point clouds [0.0]
  We leverage on point orientation distributions around a point in order to obtain an expressive local neighborhood representation for point clouds. New ODFNet model achieves state-of-the-art accuracy for object classification on ModelNet40 and ScanObjectNN datasets.
  arXiv  Detail & Related papers  (2020-12-08T19:54:20Z)
• LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts [65.79931333193016]
  We present a novel Local-Region-Context Network (LRC-Net) to learn discriminative features on point clouds. LRC-Net encodes fine-grained contexts inside and among local regions simultaneously. Results show LRC-Net is competitive with state-of-the-art methods in shape classification and shape segmentation applications.
  arXiv  Detail & Related papers  (2020-03-18T14:34:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.