Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations

• URL: http://arxiv.org/abs/2211.01174v1
• Date: Wed, 2 Nov 2022 14:49:46 GMT
• Title: Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations
• Authors: Zhuheng Lu, Peng Zhang, Yuewei Dai, Weiqing Li, and Zhiyong Su
• Abstract summary: We propose a novel weighted hypergraph convolutional network-based method, called WHCN, to confront the challenges of learning point-wise labels from scene-level annotations. Experimental results demonstrate that the proposed WHCN is effective to predict the point labels with scene annotations, and yields state-of-the-art results in the community.
• Score: 6.879675320416237
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud segmentation with scene-level annotations is a promising but challenging task. Currently, the most popular way is to employ the class activation map (CAM) to locate discriminative regions and then generate point-level pseudo labels from scene-level annotations. However, these methods always suffer from the point imbalance among categories, as well as the sparse and incomplete supervision from CAM. In this paper, we propose a novel weighted hypergraph convolutional network-based method, called WHCN, to confront the challenges of learning point-wise labels from scene-level annotations. Firstly, in order to simultaneously overcome the point imbalance among different categories and reduce the model complexity, superpoints of a training point cloud are generated by exploiting the geometrically homogeneous partition. Then, a hypergraph is constructed based on the high-confidence superpoint-level seeds which are converted from scene-level annotations. Secondly, the WHCN takes the hypergraph as input and learns to predict high-precision point-level pseudo labels by label propagation. Besides the backbone network consisting of spectral hypergraph convolution blocks, a hyperedge attention module is learned to adjust the weights of hyperedges in the WHCN. Finally, a segmentation network is trained by these pseudo point cloud labels. We comprehensively conduct experiments on the ScanNet and S3DIS segmentation datasets. Experimental results demonstrate that the proposed WHCN is effective to predict the point labels with scene annotations, and yields state-of-the-art results in the community. The source code is available at http://zhiyongsu.github.io/Project/WHCN.html.

Related papers

• High-quality Pseudo-labeling for Point Cloud Segmentation with Scene-level Annotation [32.03087826213936]
  This paper investigates indoor point cloud semantic segmentation under scene-level annotation.<n>Current methods first generate point-level pseudo-labels, which are then used to train segmentation models.<n>To enhance accuracy, this paper proposes a high-quality pseudo-label generation framework.
  arXiv  Detail & Related papers  (2025-06-29T13:17:12Z)
• ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotations [29.231508413247457]
  3D instance segmentation methods often require fully-annotated dense labels for training. We present ClickSeg, a novel click-level weakly supervised 3D instance segmentation method. ClickSeg achieves $sim$90% of the accuracy of the fully-supervised counterpart.
  arXiv  Detail & Related papers  (2023-07-19T02:49:44Z)
• FreePoint: Unsupervised Point Cloud Instance Segmentation [72.64540130803687]
  We propose FreePoint, for underexplored unsupervised class-agnostic instance segmentation on point clouds. We represent point features by combining coordinates, colors, and self-supervised deep features. Based on the point features, we segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.
  arXiv  Detail & Related papers  (2023-05-11T16:56:26Z)
• You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding [107.06117227661204]
  We propose One Thing One Click'', meaning that the annotator only needs to label one point per object. We iteratively conduct the training and label propagation, facilitated by a graph propagation module. Our model can be compatible to 3D instance segmentation equipped with a point-clustering strategy.
  arXiv  Detail & Related papers  (2023-03-26T13:57:00Z)
• Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud [69.36717778451667]
  Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. We propose an effective weakly supervised method containing two components to solve the problem. The experimental results show the large gain against existing weakly supervised and comparable results to fully supervised methods.
  arXiv  Detail & Related papers  (2022-12-09T09:42:26Z)
• Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision [65.19589997822155]
  We introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision. We show that the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.
  arXiv  Detail & Related papers  (2022-01-09T09:07:48Z)
• SCSS-Net: Superpoint Constrained Semi-supervised Segmentation Network for 3D Indoor Scenes [6.3364439467281315]
  We propose a superpoint constrained semi-supervised segmentation network for 3D point clouds, named as SCSS-Net. Specifically, we use the pseudo labels predicted from unlabeled point clouds for self-training, and the superpoints produced by geometry-based and color-based Region Growing algorithms are combined to modify and delete pseudo labels with low confidence.
  arXiv  Detail & Related papers  (2021-07-08T04:43:21Z)
• SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network [21.818744369503197]
  We propose a semi-supervised semantic point cloud segmentation network, named SSPC-Net. We train the semantic segmentation network by inferring the labels of unlabeled points from the few annotated 3D points. Our method can achieve better performance than the current semi-supervised segmentation method with fewer annotated 3D points.
  arXiv  Detail & Related papers  (2021-04-16T02:37:27Z)
• One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation [78.36781565047656]
  We propose "One Thing One Click," meaning that the annotator only needs to label one point per object. We iteratively conduct the training and label propagation, facilitated by a graph propagation module. Our results are also comparable to those of the fully supervised counterparts.
  arXiv  Detail & Related papers  (2021-04-06T02:27:25Z)
• Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds [67.0904905172941]
  We propose a weakly supervised approach to predict point-level results using weak labels on 3D point clouds. To the best of our knowledge, this is the first method that uses cloud-level weak labels on raw 3D space to train a point cloud semantic segmentation network.
  arXiv  Detail & Related papers  (2020-03-29T14:13:29Z)

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.