Projection-based Point Convolution for Efficient Point Cloud Segmentation

• URL: http://arxiv.org/abs/2202.01991v1
• Date: Fri, 4 Feb 2022 06:22:33 GMT
• Title: Projection-based Point Convolution for Efficient Point Cloud Segmentation
• Authors: Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, and Junmo Kim
• Abstract summary: Projection-based Point Convolution (PPConv) is a point convolutional module that uses 2D convolutions and multi-layer perceptrons (MLPs) as its components. PPConv achieves superior efficiency compared to state-of-the-art methods, even with a simple architecture based on PointNet++.
• Score: 24.375383511061955
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding point cloud has recently gained huge interests following the development of 3D scanning devices and the accumulation of large-scale 3D data. Most point cloud processing algorithms can be classified as either point-based or voxel-based methods, both of which have severe limitations in processing time or memory, or both. To overcome these limitations, we propose Projection-based Point Convolution (PPConv), a point convolutional module that uses 2D convolutions and multi-layer perceptrons (MLPs) as its components. In PPConv, point features are processed through two branches: point branch and projection branch. Point branch consists of MLPs, while projection branch transforms point features into a 2D feature map and then apply 2D convolutions. As PPConv does not use point-based or voxel-based convolutions, it has advantages in fast point cloud processing. When combined with a learnable projection and effective feature fusion strategy, PPConv achieves superior efficiency compared to state-of-the-art methods, even with a simple architecture based on PointNet++. We demonstrate the efficiency of PPConv in terms of the trade-off between inference time and segmentation performance. The experimental results on S3DIS and ShapeNetPart show that PPConv is the most efficient method among the compared ones. The code is available at github.com/pahn04/PPConv.

Related papers

• Dynamic 3D Point Cloud Sequences as 2D Videos [81.46246338686478]
  3D point cloud sequences serve as one of the most common and practical representation modalities of real-world environments. We propose a novel generic representation called textitStructured Point Cloud Videos (SPCVs) SPCVs re-organizes a point cloud sequence as a 2D video with spatial smoothness and temporal consistency, where the pixel values correspond to the 3D coordinates of points.
  arXiv  Detail & Related papers  (2024-03-02T08:18:57Z)
• PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction [72.75478398447396]
  We propose a cylindrical tri-perspective view to represent point clouds effectively and comprehensively. Considering the distance distribution of LiDAR point clouds, we construct the tri-perspective view in the cylindrical coordinate system. We employ spatial group pooling to maintain structural details during projection and adopt 2D backbones to efficiently process each TPV plane.
  arXiv  Detail & Related papers  (2023-08-31T17:57:17Z)
• DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds [42.64433313672884]
  We regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation preserves most points. We also present a novel warping projection technique to alleviate the information loss problem.
  arXiv  Detail & Related papers  (2023-08-08T16:37:24Z)
• PointConvFormer: Revenge of the Point-based Convolution [7.539787913497268]
  We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative position, and Transformers which utilize feature-based attention. Our results show that PointConvFormer offers a better accuracy-speed tradeoff than classic convolutions, regular transformers, and voxelized sparse convolution approaches.
  arXiv  Detail & Related papers  (2022-08-04T20:31:46Z)
• 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)
• PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths [60.32185890237936]
  We design a novel neural network, named PMP-Net++, to mimic behavior of an earth mover. It moves each point of incomplete input to obtain a complete point cloud, where total distance of point moving paths (PMPs) should be the shortest. The network learns a strict and unique correspondence on point-level, and thus improves quality of predicted complete shape.
  arXiv  Detail & Related papers  (2022-02-19T03:00:40Z)
• The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions [15.997907568429177]
  This paper investigates different variants of PointConv, a convolution network on point clouds, to examine their robustness to input scale and rotation changes. We derive a novel viewpoint-invariant descriptor by utilizing 3D geometric properties as the input to PointConv. Experiments are conducted on the 2D MNIST & CIFAR-10 datasets as well as the 3D Semantic KITTI & ScanNet dataset.
  arXiv  Detail & Related papers  (2021-01-19T19:32:38Z)
• Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds [2.924868086534434]
  This paper introduces a novel approach for 3D point cloud semantic segmentation that exploits multiple projections of the point cloud. Our Multi-Projection Fusion framework analyzes spherical and bird's-eye view projections using two separate highly-efficient 2D fully convolutional models.
  arXiv  Detail & Related papers  (2020-11-03T19:40:43Z)
• Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds [145.79324955896845]
  We propose a permutable anisotropic convolutional operation (PAI-Conv) that calculates soft-permutation matrices for each point. Experiments on point clouds demonstrate that PAI-Conv produces competitive results in classification and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2020-05-27T02:42:29Z)
• FPConv: Learning Local Flattening for Point Convolution [64.01196188303483]
  We introduce FPConv, a novel surface-style convolution operator designed for 3D point cloud analysis. Unlike previous methods, FPConv doesn't require transforming to intermediate representation like 3D grid or graph. FPConv can be easily integrated into various network architectures for tasks like 3D object classification and 3D scene segmentation.
  arXiv  Detail & Related papers  (2020-02-25T07:15:08Z)

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.