Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation

Jiang, Li; Zhao, Hengshuang; Liu, Shu; Shen, Xiaoyong; Fu, Chi‐Wing; Jia, Jiaya

doi:10.1109/iccv.2019.01053

Cited by 203 publications

(85 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Representation Learning on Point Clouds. Recently representation learning on point clouds has drawn lots of attention for improving the performance of point cloud classification and segmentation [10], [18], [19], [68], [69], [70], [71], [72], [73], [74], [75], [76], [77], [78], [79]. In terms of 3D detection, previous methods generally project the point clouds to regular bird view grids [9], [12] or 3D voxels [10], [80] for processing point clouds with 2D/3D CNN.…”

Section: D Object Detection With Point Cloudsmentioning

confidence: 99%

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Shi

Guo²,

Jiang³

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

1,580

1,045

View full text Add to dashboard Cite

3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose the Point-Voxel Region based Convolution Neural Networks (PV-RCNNs) for accurate 3D detection from point clouds. First, we propose a novel 3D object detector, PV-RCNN-v1, which employs the voxel-to-keypoint scene encoding and keypoint-to-grid RoI feature abstraction two novel steps. These two steps deeply incorporate both 3D voxel CNN and PointNet-based set abstraction for learning discriminative point-cloud features. Second, we propose a more advanced framework, PV-RCNN-v2, for more efficient and accurate 3D detection. It consists of two major improvements, where the first one is the sectorized proposal-centric strategy for efficiently producing more representative and uniformly distributed keypoints, and the second one is the VectorPool aggregation to replace set abstraction for better aggregating local point-cloud features with much less resource consumption. With these two major modifications, our PV-RCNN-v2 runs more than twice as fast as the v1 version while still achieving better performance on the large-scale Waymo Open Dataset with 150m × 150m detection range. Extensive experiments demonstrate that our proposed PV-RCNNs significantly outperform previous state-of-the-art 3D detection methods on both the Waymo Open Dataset and the highly-competitive KITTI benchmark.

show abstract

Section: D Object Detection With Point Cloudsmentioning

confidence: 99%

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Shi

Guo²,

Jiang³

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

1,580

1,045

View full text Add to dashboard Cite

show abstract

“…Some works directly use point clouds as input [34][35][36][37][38][39]. Point-Net uses the shared multilayer perceptions (MLP) to learn per-point features, and uses max-pooling for global feature to solve the unordered data question [20].…”

Section: Basic Point-based Networkmentioning

confidence: 99%

Semantic segmentation of large-scale point clouds based on dilated nearest neighbors graph

Wang

Liu

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Three-dimensional (3D) semantic segmentation of point clouds is important in many scenarios, such as automatic driving, robotic navigation, while edge computing is indispensable in the devices. Deep learning methods based on point sampling prove to be computation and memory efficient to tackle large-scale point clouds (e.g. millions of points). However, some local features may be abandoned while sampling. In this paper, We present one end-to-end 3D semantic segmentation framework based on dilated nearest neighbor encoding. Instead of down-sampling point cloud directly, we propose a dilated nearest neighbor encoding module to broaden the network’s receptive field to learn more 3D geometric information. Without increase of network parameters, our method is computation and memory efficient for large-scale point clouds. We have evaluated the dilated nearest neighbor encoding in two different networks. The first is the random sampling with local feature aggregation. The second is the Point Transformer. We have evaluated the quality of the semantic segmentation on the benchmark 3D dataset S3DIS, and demonstrate that the proposed dilated nearest neighbor encoding exhibited stable advantages over baseline and competing methods.

show abstract

“…Other Point Networks: There are also special networks developed for various applications to directly take raw points as input for sampling [58,60], semantic [17,39,51,59,63,64], and instance segmentation [33,57] basis point sets [34], multi-resolution tree-structured networks [5], bilateral convolutions on a sparse lattice of the point cloud [42], recurrent neural networks (RNN) on slices of a point cloud [15], and the superpoint graph-based semantic segmentation [22].…”

Section: Point-wise Convolutionsmentioning

confidence: 99%

Deep FusionNet for Point Cloud Semantic Segmentation

Zhang

Jin

Wah

et al. 2020

Lecture Notes in Computer Science

130

View full text Add to dashboard Cite

Many point cloud segmentation methods rely on transferring irregular points into a voxel-based regular representation. Although voxel-based convolutions are useful for feature aggregation, they produce ambiguous or wrong predictions if a voxel contains points from different classes. Other approaches (such as PointNets and point-wise convolutions) can take irregular points for feature learning. But their high memory and computational costs (such as for neighborhood search and ball-querying) limit their ability and accuracy for large-scale point cloud processing. To address these issues, we propose a deep fusion network architecture (FusionNet) with a unique voxel-based "mini-PointNet" point cloud representation and a new feature aggregation module (fusion module) for large-scale 3D semantic segmentation. Our FusionNet can learn more accurate point-wise predictions when compared to voxel-based convolutional networks. It can realize more effective feature aggregations with lower memory and computational complexity for large-scale point cloud segmentation when compared to the popular point-wise convolutions. Our experimental results show that FusionNet can take more than one million points on one GPU for training to achieve state-of-the-art accuracy on large-scale Semantic KITTI benchmark. The code will be available at https://github.com/feihuzhang/LiDARSeg.

show abstract

Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation

Cited by 203 publications

References 21 publications

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

Semantic segmentation of large-scale point clouds based on dilated nearest neighbors graph

Deep FusionNet for Point Cloud Semantic Segmentation

Contact Info

Product

Resources

About