On-the-fly Point Feature Representation for Point Clouds Analysis

• URL: http://arxiv.org/abs/2407.21335v2
• Date: Mon, 12 Aug 2024 08:21:36 GMT
• Title: On-the-fly Point Feature Representation for Point Clouds Analysis
• Authors: Jiangyi Wang, Zhongyao Cheng, Na Zhao, Jun Cheng, Xulei Yang,
• Abstract summary: We propose On-the-fly Point Feature Representation (OPFR), which captures abundant geometric information explicitly through Curve Feature Generator module. We also introduce the Local Reference Constructor module, which approximates the local coordinate systems based on triangle sets. OPFR only requires extra 1.56ms for inference (65x faster than vanilla PFH) and 0.012M more parameters, and it can serve as a versatile plug-and-play module for various backbones.
• Score: 7.074010861305738
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud analysis is challenging due to its unique characteristics of unorderness, sparsity and irregularity. Prior works attempt to capture local relationships by convolution operations or attention mechanisms, exploiting geometric information from coordinates implicitly. These methods, however, are insufficient to describe the explicit local geometry, e.g., curvature and orientation. In this paper, we propose On-the-fly Point Feature Representation (OPFR), which captures abundant geometric information explicitly through Curve Feature Generator module. This is inspired by Point Feature Histogram (PFH) from computer vision community. However, the utilization of vanilla PFH encounters great difficulties when applied to large datasets and dense point clouds, as it demands considerable time for feature generation. In contrast, we introduce the Local Reference Constructor module, which approximates the local coordinate systems based on triangle sets. Owing to this, our OPFR only requires extra 1.56ms for inference (65x faster than vanilla PFH) and 0.012M more parameters, and it can serve as a versatile plug-and-play module for various backbones, particularly MLP-based and Transformer-based backbones examined in this study. Additionally, we introduce the novel Hierarchical Sampling module aimed at enhancing the quality of triangle sets, thereby ensuring robustness of the obtained geometric features. Our proposed method improves overall accuracy (OA) on ModelNet40 from 90.7% to 94.5% (+3.8%) for classification, and OA on S3DIS Area-5 from 86.4% to 90.0% (+3.6%) for semantic segmentation, respectively, building upon PointNet++ backbone. When integrated with Point Transformer backbone, we achieve state-of-the-art results on both tasks: 94.8% OA on ModelNet40 and 91.7% OA on S3DIS Area-5.

Related papers

• X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition [73.0588783479853]
  X-3D is an explicit 3D structure modeling approach. It captures explicit local structural information within the input 3D space. It produces dynamic kernels with shared weights for all neighborhood points within the current local region.
  arXiv  Detail & Related papers  (2024-04-23T13:15:35Z)
• 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)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• GAM : Gradient Attention Module of Optimization for Point Clouds Analysis [8.986123309626551]
  In point cloud analysis tasks, the existing local feature aggregation descriptors (LFAD) are unable to fully utilize information in the neighborhood of central points. We propose a gradient-based local attention module, termed as Gradient Attention Module (GAM) to address the aforementioned problem. GAM achieves the best performance among current point-based models with mIoU/OA/mAcc of 74.4%/90.6%/83.2%, respectively.
  arXiv  Detail & Related papers  (2023-03-19T02:51:14Z)
• GeoSpark: Sparking up Point Cloud Segmentation with Geometry Clue [25.747471104753426]
  GeoSpark is a Plug-in module that incorporates geometry clues into the network to Spark up feature learning and downsampling. For feature aggregation, GeoSpark improves by allowing the network to learn from both local points and neighboring geometry partitions. GeoSpark utilizes geometry partition information to guide the downsampling process, where points with unique features are preserved while redundant points are fused.
  arXiv  Detail & Related papers  (2023-03-14T23:30:46Z)
• GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation [73.77505964222632]
  We present a learning-based method, namely GeoUDF, to tackle the problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation. To extract triangle meshes from the predicted UDF, we propose a customized edge-based marching cube module.
  arXiv  Detail & Related papers  (2022-11-30T06:02:01Z)
• Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework [55.40001810884942]
  We introduce a pure residual network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. Compared to most recent CurveNet, PointMLP trains 2x faster, tests 7x faster, and is more accurate on ModelNet40 benchmark.
  arXiv  Detail & Related papers  (2022-02-15T01:39:07Z)
• Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation [10.2254921311882]
  We present an innovative two-headed attention layer that combines geometric and latent features to segment a 3D scene into meaningful subsets. Each head combines local and global information, using either the geometric or latent features, of a neighborhood of points and uses this information to learn better local relationships.
  arXiv  Detail & Related papers  (2021-10-30T11:20:56Z)
• Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis [20.06552864449279]
  We present a novel method for aggregating hypothetical curves in point clouds. Sequences of connected points (curves) are initially grouped by taking guided walks in the point clouds. We provide an effective implementation of the proposed aggregation strategy.
  arXiv  Detail & Related papers  (2021-05-04T05:03:47Z)
• PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling [103.09504572409449]
  We propose a novel deep neural network based method, called PUGeo-Net, to generate uniform dense point clouds. Thanks to its geometry-centric nature, PUGeo-Net works well for both CAD models with sharp features and scanned models with rich geometric details.
  arXiv  Detail & Related papers  (2020-02-24T14:13:29Z)

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.