Semantic Segmentation on 3D Point Clouds with High Density Variations

• URL: http://arxiv.org/abs/2307.01489v1
• Date: Tue, 4 Jul 2023 05:44:13 GMT
• Title: Semantic Segmentation on 3D Point Clouds with High Density Variations
• Authors: Ryan Faulkner, Luke Haub, Simon Ratcliffe, Ian Reid, Tat-Jun Chin
• Abstract summary: HDVNet contains a nested set of encoder-decoder pathways, each handling a specific point density range. By effectively handling input density variations, HDVNet outperforms state-of-the-art models in segmentation accuracy on real point clouds with inconsistent density.
• Score: 44.467561618769714
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LiDAR scanning for surveying applications acquire measurements over wide areas and long distances, which produces large-scale 3D point clouds with significant local density variations. While existing 3D semantic segmentation models conduct downsampling and upsampling to build robustness against varying point densities, they are less effective under the large local density variations characteristic of point clouds from surveying applications. To alleviate this weakness, we propose a novel architecture called HDVNet that contains a nested set of encoder-decoder pathways, each handling a specific point density range. Limiting the interconnections between the feature maps enables HDVNet to gauge the reliability of each feature based on the density of a point, e.g., downweighting high density features not existing in low density objects. By effectively handling input density variations, HDVNet outperforms state-of-the-art models in segmentation accuracy on real point clouds with inconsistent density, using just over half the weights.

Related papers

• DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds [30.54110361164338]
  Local features and contextual dependencies are crucial for 3D point cloud analysis. We propose density adaptive convolution, coined DAConv. IAM embeds spatial information into channel attention along different spatial directions.
  arXiv  Detail & Related papers  (2023-03-08T09:46:31Z)
• Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection [85.08249413137558]
  LiDAR-produced point clouds are the major source for most state-of-the-art 3D object detectors. Small, distant, and incomplete objects with sparse or few points are often hard to detect. We present Sparse2Dense, a new framework to efficiently boost 3D detection performance by learning to densify point clouds in latent space.
  arXiv  Detail & Related papers  (2022-11-23T16:01:06Z)
• Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation [78.6612285236938]
  We propose a novel DAT (textbfDual textbfAdaptive textbfTransformations) model for weakly supervised point cloud segmentation. We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets.
  arXiv  Detail & Related papers  (2022-07-19T05:43:14Z)
• Density-preserving Deep Point Cloud Compression [72.0703956923403]
  We propose a novel deep point cloud compression method that preserves local density information. Our method works in an auto-encoder fashion: the encoder downsamples the points and learns point-wise features, while the decoder upsamples the points using these features.
  arXiv  Detail & Related papers  (2022-04-27T03:42:15Z)
• Point Density-Aware Voxels for LiDAR 3D Object Detection [8.136649838488042]
  Point Density-Aware Voxel network (PDV) is an end-to-end two stage LiDAR 3D object detection architecture. PDV efficiently localizes voxel features from the 3D sparse backbone through voxel point centroids. PDV outperforms all state-of-the-art methods on the Open dataset.
  arXiv  Detail & Related papers  (2022-03-10T22:11:06Z)
• A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion [69.32451612060214]
  Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
  arXiv  Detail & Related papers  (2021-12-07T06:59:06Z)
• Deep Point Cloud Reconstruction [74.694733918351]
  Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. We propose a deep point cloud reconstruction network consisting of two stages: 1) a 3D sparse stacked-hourglass network as for the initial densification and denoising, 2) a refinement via transformers converting the discrete voxels into 3D points.
  arXiv  Detail & Related papers  (2021-11-23T07:53:28Z)
• A Density-Aware PointRCNN for 3D Object Detection in Point Clouds [12.077854878153513]
  We present an improved version of PointRCNN for 3D object detection. A multi-branch backbone network is adopted to handle the non-uniform density of point clouds.
  arXiv  Detail & Related papers  (2020-09-11T09:35:13Z)
• MNEW: Multi-domain Neighborhood Embedding and Weighting for Sparse Point Clouds Segmentation [1.2380933178502298]
  We propose MNEW, including multi-domain neighborhood embedding, and attention weighting based on their geometry distance, feature similarity, and neighborhood sparsity. MNEW achieves the top performance for sparse point clouds, which is important to the application of LiDAR-based automated driving perception.
  arXiv  Detail & Related papers  (2020-04-05T18:02:07Z)

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.