mlsanityData to 14 Oct 2026

CurveCloudNet: Processing Point Clouds with 1D Structure

arXiv 2303.12050 ↗First posted 21 Mar 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene, resulting in a point cloud with notable 1D curve-like structures. In this work, we introduce a new point cloud processing scheme and backbone, called CurveCloudNet, which takes advantage of the curve-like structure inherent to these sensors. While existing backbones discard the rich 1D traversal patterns and rely on generic 3D operations, CurveCloudNet parameterizes the point cloud as a collection of polylines (dubbed a "curve cloud"), establishing a local surface-aware ordering on the points. By reasoning along curves, CurveCloudNet captures lightweight curve-aware priors to efficiently and accurately reason in several diverse 3D environments. We evaluate CurveCloudNet on multiple synthetic and real datasets that exhibit distinct 3D size and structure. We demonstrate that CurveCloudNet outperforms both point-based and sparse-voxel backbones in various segmentation settings, notably scaling to large scenes better than point-based alternatives while exhibiting improved single-object performance over sparse-voxel alternatives. In all, CurveCloudNet is an efficient and accurate backbone that can handle a larger variety of 3D environments than past works.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 72 of its 96 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

72 of 96 references.

References · 72

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  9. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  11. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  12. 2020Point Transformercited by 1,470
38 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  3. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  4. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  5. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  6. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  7. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  8. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  9. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  10. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  11. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  12. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  13. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  14. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  15. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  16. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  17. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  18. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  19. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 248
  20. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  21. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
  22. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  23. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  24. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  25. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  26. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  27. 2020A2D2: Audi Autonomous Driving Datasetcited by 190
  28. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  29. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  30. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  31. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  32. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  33. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  34. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  35. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  36. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  37. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 142
  38. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 3.

5 papers.

  1. 2024Towards Realistic Scene Generation with LiDAR Diffusion Modelscited by 69
  2. 2025A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generationcited by 4
  3. 2026TowerDataset: A Heterogeneous Benchmark for Transmission Corridor Segmentation with a Global-Local Fusion Frameworkcited by 0
  4. 2026A Robust Point Cloud Analysis Framework Inspired By Primary Visual Cortexcited by 0
  5. 2026T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generationcited by 0