Related papers: Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection

Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection

URL: http://arxiv.org/abs/2304.02867v2
Date: Sun, 3 Mar 2024 15:15:05 GMT
Title: Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection
Authors: Yuhao Huang, Sanping Zhou, Junjie Zhang, Jinpeng Dong, Nanning Zheng
Abstract summary: We develop a sparse voxel-pillar encoder that encodes point clouds into voxel and pillar features through 3D and 2D sparse convolutions respectively. Our efficient, fully sparse method can be seamlessly integrated into both dense and sparse detectors.
Score: 49.324070632356296
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Efficient representation of point clouds is fundamental for LiDAR-based 3D object detection. While recent grid-based detectors often encode point clouds into either voxels or pillars, the distinctions between these approaches remain underexplored. In this paper, we quantify the differences between the current encoding paradigms and highlight the limited vertical learning within. To tackle these limitations, we introduce a hybrid Voxel-Pillar Fusion network (VPF), which synergistically combines the unique strengths of both voxels and pillars. Specifically, we first develop a sparse voxel-pillar encoder that encodes point clouds into voxel and pillar features through 3D and 2D sparse convolutions respectively, and then introduce the Sparse Fusion Layer (SFL), facilitating bidirectional interaction between sparse voxel and pillar features. Our efficient, fully sparse method can be seamlessly integrated into both dense and sparse detectors. Leveraging this powerful yet straightforward framework, VPF delivers competitive performance, achieving real-time inference speeds on the nuScenes and Waymo Open Dataset. The code will be available.

Related papers

PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection [59.355022416218624]
integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. We propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN) PVAFN uses a multi-pooling strategy to integrate both multi-scale and region-specific information effectively.
arXiv Detail & Related papers (2024-08-26T19:43:01Z)
Point Cloud Compression with Implicit Neural Representations: A Unified Framework [54.119415852585306]
We present a pioneering point cloud compression framework capable of handling both geometry and attribute components. Our framework utilizes two coordinate-based neural networks to implicitly represent a voxelized point cloud. Our method exhibits high universality when contrasted with existing learning-based techniques.
arXiv Detail & Related papers (2024-05-19T09:19:40Z)
FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection [19.419030878019974]
unstructured 3D point clouds are filled in the 2D plane and 3D point cloud features are extracted faster using projection-aware convolution layers. The corresponding indexes between different sensor signals are established in advance in the data preprocessing. Two new plug-and-play fusion modules, LiCamFuse and BiLiCamFuse, are proposed.
arXiv Detail & Related papers (2022-09-15T16:13:19Z)
Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds [16.69887974230884]
Transformer has demonstrated promising performance in many 2D vision tasks. It is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space. Existing methods usually compute self-attention locally by grouping the points into clusters of the same size, or perform convolutional self-attention on a discretized representation. We propose a novel voxel-based architecture, namely Voxel Set Transformer (VoxSeT), to detect 3D objects from point clouds by means of set-to-set translation.
arXiv Detail & Related papers (2022-03-19T12:31:46Z)
Voxel Transformer for 3D Object Detection [133.34678177431914]
Voxel Transformer (VoTr) is a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Our proposed VoTr shows consistent improvement over the convolutional baselines while maintaining computational efficiency on the KITTI dataset and the Open dataset.
arXiv Detail & Related papers (2021-09-06T14:10:22Z)
Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation [81.08111209632501]
We propose a geometry-aware stereo-LiDAR fusion network for long-range depth estimation. We exploit sparse and accurate point clouds as a cue for guiding correspondences of stereo images in a unified 3D volume space. Our network achieves state-of-the-art performance on the KITTI and the Virtual- KITTI datasets.
arXiv Detail & Related papers (2021-03-24T03:24:46Z)
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)
Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds [76.52448276587707]
We propose Reconfigurable Voxels, a new approach to constructing representations from 3D point clouds. Specifically, we devise a biased random walk scheme, which adaptively covers each neighborhood with a fixed number of voxels. We find that this approach effectively improves the stability of voxel features, especially for sparse regions.
arXiv Detail & Related papers (2020-04-06T15:07:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.