Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation

• URL: http://arxiv.org/abs/2009.08924v1
• Date: Fri, 18 Sep 2020 16:42:02 GMT
• Title: Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation
• Abstract summary: We present MuGNet, a memory-efficient, end-to-end graph neural network framework to perform semantic segmentation on large-scale pointclouds. We demonstrate that our framework can process up to 45 room scans at once on a single 11 GB GPU.
• Score: 0.3867363075280543
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a multi-resolution deep-learning architecture to semantically segment dense large-scale pointclouds. Dense pointcloud data require a computationally expensive feature encoding process before semantic segmentation. Previous work has used different approaches to drastically downsample from the original pointcloud so common computing hardware can be utilized. While these approaches can relieve the computation burden to some extent, they are still limited in their processing capability for multiple scans. We present MuGNet, a memory-efficient, end-to-end graph neural network framework to perform semantic segmentation on large-scale pointclouds. We reduce the computation demand by utilizing a graph neural network on the preformed pointcloud graphs and retain the precision of the segmentation with a bidirectional network that fuses feature embedding at different resolutions. Our framework has been validated on benchmark datasets including Stanford Large-Scale 3D Indoor Spaces Dataset(S3DIS) and Virtual KITTI Dataset. We demonstrate that our framework can process up to 45 room scans at once on a single 11 GB GPU while still surpassing other graph-based solutions for segmentation on S3DIS with an 88.5\% (+3\%) overall accuracy and 69.8\% (+7.7\%) mIOU accuracy.

Related papers

• Clustering based Point Cloud Representation Learning for 3D Analysis [80.88995099442374]
  We propose a clustering based supervised learning scheme for point cloud analysis. Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space. Our algorithm shows notable improvements on famous point cloud segmentation datasets.
  arXiv  Detail & Related papers  (2023-07-27T03:42:12Z)
• SATR: Zero-Shot Semantic Segmentation of 3D Shapes [74.08209893396271]
  We explore the task of zero-shot semantic segmentation of 3D shapes by using large-scale off-the-shelf 2D image recognition models. We develop the Assignment with Topological Reweighting (SATR) algorithm and evaluate it on ShapeNetPart and our proposed FAUST benchmarks. SATR achieves state-of-the-art performance and outperforms a baseline algorithm by 1.3% and 4% average mIoU.
  arXiv  Detail & Related papers  (2023-04-11T00:43:16Z)
• Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network [22.9434434107516]
  We develop a new multi-layer transformer network for few-shot point cloud semantic segmentation. Our method achieves the new state-of-the-art performance, with 15% less inference time, over existing few-shot 3D point cloud segmentation models.
  arXiv  Detail & Related papers  (2023-03-28T00:27:54Z)
• Learning task-specific features for 3D pointcloud graph creation [0.8629912408966145]
  We propose a principled way of creating a graph from a 3D pointcloud. Our method is based on performing k-NN over a transformation of the input 3D pointcloud. We also introduce a regularization method based on stress minimization, which allows to control how distant is the learnt graph from our baseline: k-NN over xyz space.
  arXiv  Detail & Related papers  (2022-09-02T11:13:02Z)
• 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)
• Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation [18.81644604997336]
  We propose Point-Unet, a novel method that incorporates the efficiency of deep learning with 3D point clouds into volumetric segmentation. Our key idea is to first predict the regions of interest in the volume by learning an attentional probability map. A comprehensive benchmark on different metrics has shown that our context-aware Point-Unet robustly outperforms the SOTA voxel-based networks.
  arXiv  Detail & Related papers  (2022-03-16T22:02:08Z)
• GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds [64.86292006892093]
  GSIP (Green of Indoor Point clouds) is an efficient solution to semantic segmentation of large-scale indoor scene point clouds. GSIP has two novel components: 1) a room-style data pre-processing method that selects a proper subset of points for further processing, and 2) a new feature extractor which is extended from PointHop. Experiments show that GSIP outperforms PointNet in segmentation performance for the S3DIS dataset.
  arXiv  Detail & Related papers  (2021-09-24T09:26:53Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)
• Scaling Graph Neural Networks with Approximate PageRank [64.92311737049054]
  We present the PPRGo model which utilizes an efficient approximation of information diffusion in GNNs. In addition to being faster, PPRGo is inherently scalable, and can be trivially parallelized for large datasets like those found in industry settings. We show that training PPRGo and predicting labels for all nodes in this graph takes under 2 minutes on a single machine, far outpacing other baselines on the same graph.
  arXiv  Detail & Related papers  (2020-07-03T09:30:07Z)
• Learning to Segment 3D Point Clouds in 2D Image Space [20.119802932358333]
  We show how to efficiently project 3D point clouds into a 2D image space. Traditional 2D convolutional neural networks (CNNs) such as U-Net can be applied for segmentation.
  arXiv  Detail & Related papers  (2020-03-12T03:18:59Z)
• Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud [3.04585143845864]
  We propose a graph neural network to detect objects from a LiDAR point cloud. We encode the point cloud efficiently in a fixed radius near-neighbors graph. In Point-GNN, we propose an auto-registration mechanism to reduce translation variance.
  arXiv  Detail & Related papers  (2020-03-02T23:44:12Z)

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.