Fast Point Voxel Convolution Neural Network with Selective Feature Fusion for Point Cloud Semantic Segmentation

• URL: http://arxiv.org/abs/2109.11614v1
• Date: Thu, 23 Sep 2021 19:39:01 GMT
• Title: Fast Point Voxel Convolution Neural Network with Selective Feature Fusion for Point Cloud Semantic Segmentation
• Authors: Xu Wang, Yuyan Li, Ye Duan
• Abstract summary: We present a novel lightweight convolutional neural network for point cloud analysis. Our method operates on the entire point sets without sampling and achieves good performances efficiently.
• Score: 7.557684072809662
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a novel lightweight convolutional neural network for point cloud analysis. In contrast to many current CNNs which increase receptive field by downsampling point cloud, our method directly operates on the entire point sets without sampling and achieves good performances efficiently. Our network consists of point voxel convolution (PVC) layer as building block. Each layer has two parallel branches, namely the voxel branch and the point branch. For the voxel branch specifically, we aggregate local features on non-empty voxel centers to reduce geometric information loss caused by voxelization, then apply volumetric convolutions to enhance local neighborhood geometry encoding. For the point branch, we use Multi-Layer Perceptron (MLP) to extract fine-detailed point-wise features. Outputs from these two branches are adaptively fused via a feature selection module. Moreover, we supervise the output from every PVC layer to learn different levels of semantic information. The final prediction is made by averaging all intermediate predictions. We demonstrate empirically that our method is able to achieve comparable results while being fast and memory efficient. We evaluate our method on popular point cloud datasets for object classification and semantic segmentation tasks.

Related papers

• VTPNet for 3D deep learning on point cloud [10.470127366415813]
  Voxel-Transformer-Point (VTP) Block for extracting local and global features of point clouds. VTP combines the advantages of voxel-based, point-based and Transformer-based methods. Experiments indicate that VTPNet has good performance in 3D point cloud learning.
  arXiv  Detail & Related papers  (2023-05-10T13:07:46Z)
• Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space [25.57569871876213]
  We propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space (content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class. We also introduce an Inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately.
  arXiv  Detail & Related papers  (2023-03-08T14:11:05Z)
• 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)
• CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning [81.85951026033787]
  We set transformers in this work and incorporate them into a hierarchical framework for shape classification and part and scene segmentation. We also compute efficient and dynamic global cross attentions by leveraging sampling and grouping at each iteration. The proposed hierarchical model achieves state-of-the-art shape classification in mean accuracy and yields results on par with the previous segmentation methods.
  arXiv  Detail & Related papers  (2022-07-31T21:39:15Z)
• SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation [94.11915008006483]
  We propose SemAffiNet for point cloud semantic segmentation. We conduct extensive experiments on the ScanNetV2 and NYUv2 datasets.
  arXiv  Detail & Related papers  (2022-05-26T17:00:23Z)
• Stratified Transformer for 3D Point Cloud Segmentation [89.9698499437732]
  Stratified Transformer is able to capture long-range contexts and demonstrates strong generalization ability and high performance. To combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information. Experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets.
  arXiv  Detail & Related papers  (2022-03-28T05:35:16Z)
• CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning [53.1436669083784]
  We propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guide self-supervised reconstruction to learn semantic content in the point cloud. For classification, we get a competitive result with the fully-supervised methods on ModelNet40 (92.5% accuracy) and ScanObjectNN (87.9% accuracy)
  arXiv  Detail & Related papers  (2022-01-20T15:04:12Z)
• 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)
• Learning-based lossless compression of 3D point cloud geometry [11.69103847045569]
  encoder operates in a hybrid mode, mixing octree and voxel-based coding. Our method outperforms the state-of-the-art MPEG G-PCC standard with average rate savings of 28%.
  arXiv  Detail & Related papers  (2020-11-30T11:27:16Z)
• Refinement of Predicted Missing Parts Enhance Point Cloud Completion [62.997667081978825]
  Point cloud completion is the task of predicting complete geometry from partial observations using a point set representation for a 3D shape. Previous approaches propose neural networks to directly estimate the whole point cloud through encoder-decoder models fed by the incomplete point set. This paper proposes an end-to-end neural network architecture that focuses on computing the missing geometry and merging the known input and the predicted point cloud.
  arXiv  Detail & Related papers  (2020-10-08T22:01:23Z)
• Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation [37.33261773707134]
  The proposed network aims to build the long-range dependencies of point clouds for the accurate segmentation. We develop a novel cascaded non-local module, which consists of the neighborhood-level, superpoint-level and global-level non-local blocks. Our method achieves state-of-the-art performance and effectively reduces the time consumption and memory occupation.
  arXiv  Detail & Related papers  (2020-07-30T14:34:43Z)

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.