EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation
Not on the map. Why?
Abstract (arXiv)
Point cloud patterns are hard to learn because of the implicit local geometry features among the orderless points. In recent years, point cloud representation in 2D space has attracted increasing research interest since it exposes the local geometry features in a 2D space. By projecting those points to a 2D feature map, the relationship between points is inherited in the context between pixels, which are further extracted by a 2D convolutional neural network. However, existing 2D representing methods are either accuracy limited or time-consuming. In this paper, we propose a novel 2D representation method that projects a point cloud onto an ellipsoid surface space, where local patterns are well exposed in ellipsoid-level and point-level. Additionally, a novel convolutional neural network named EllipsoidNet is proposed to utilize those features for point cloud classification and segmentation applications. The proposed methods are evaluated in ModelNet40 and ShapeNet benchmarks, where the advantages are clearly shown over existing 2D representation methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 41 of its 56 references that are in the map. First posted on arXiv 3 Mar 2021.
Builds on
41 of 56 references.
References · 41
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
- 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
- 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
- 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
- 2018PointCNN: Convolution On X-Transformed Pointscited by 764
- 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
29 more
- 2019Panoptic Feature Pyramid Networkscited by 644
- 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
- 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
- 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
- 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
- 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
- 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
- 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
- 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
- 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
- 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
- 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
- 2019CvxNet: Learnable Convex Decompositioncited by 173
- 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
- 2017Pointwise Convolutional Neural Networkscited by 126
- 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
- 2019Interpolated Convolutional Networks for 3D Point Cloud Understandingcited by 86
- 2017Deep Projective 3D Semantic Segmentationcited by 81
- 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
- 2019A-CNN: Annularly Convolutional Neural Networks on Point Cloudscited by 66
- 2018VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentationcited by 64
- 2019Octree guided CNN with Spherical Kernels for 3D Point Cloudscited by 50
- 2017O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysiscited by 47
- 2019PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentationcited by 44
- 2020Learning to Segment 3D Point Clouds in 2D Image Spacecited by 24
- 2020LodoNet: A Deep Neural Network with 2D Keypoint Matchingfor 3D LiDAR Odometry Estimationcited by 19
- 2020TreeRNN: Topology-Preserving Deep GraphEmbedding and Learningcited by 7
- 2018ChipNet: Real-Time LiDAR Processing for Drivable Region Segmentation on an FPGAcited by 5
- 2017Real-Time Road Segmentation Using LiDAR Data Processing on an FPGAcited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.