mlsanityData to 14 Oct 2026

Surface Representation for Point Clouds

arXiv 2205.05740 ↗First posted 11 May 2022cs.CV cs.AI cs.GRcited by 84

Not on the map. Why?

Abstract (arXiv)

Most prior work represents the shapes of point clouds by coordinates. However, it is insufficient to describe the local geometry directly. In this paper, we present RepSurf (representative surfaces), a novel representation of point clouds to explicitly depict the very local structure. We explore two variants of RepSurf, Triangular RepSurf and Umbrella RepSurf inspired by triangle meshes and umbrella curvature in computer graphics. We compute the representations of RepSurf by predefined geometric priors after surface reconstruction. RepSurf can be a plug-and-play module for most point cloud models thanks to its free collaboration with irregular points. Based on a simple baseline of PointNet++ (SSG version), Umbrella RepSurf surpasses the previous state-of-the-art by a large margin for classification, segmentation and detection on various benchmarks in terms of performance and efficiency. With an increase of around 0.008M number of parameters, 0.04G FLOPs, and 1.12ms inference time, our method achieves 94.7% (+0.5%) on ModelNet40, and 84.6% (+1.8%) on ScanObjectNN for classification, while 74.3% (+0.8%) mIoU on S3DIS 6-fold, and 70.0% (+1.6%) mIoU on ScanNet for segmentation. For detection, previous state-of-the-art detector with our RepSurf obtains 71.2% (+2.1%) mAPmathit25, 54.8% (+2.0%) mAPmathit50 on ScanNetV2, and 64.9% (+1.9%) mAPmathit25, 47.7% (+2.5%) mAPmathit50 on SUN RGB-D. Our lightweight Triangular RepSurf performs its excellence on these benchmarks as well. The code is publicly available at urlhttps://github.com/hancyran/RepSurf.

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). Builds on 56 of its 79 references that are in the map. First posted on arXiv 11 May 2022.

Builds on

56 of 79 references.

References · 56

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2020Point Transformercited by 1,470
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  12. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
38 more
  1. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  2. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  3. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  4. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  5. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  8. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  9. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  10. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  11. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  12. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  13. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 326
  14. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  15. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  16. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  17. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  18. 2017Submanifold Sparse Convolutional Networkscited by 223
  19. 2021Group-Free 3D Object Detection via Transformerscited by 215
  20. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  21. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  22. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  23. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  24. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  25. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  26. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  27. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  28. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  29. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  30. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  31. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  32. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  33. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  34. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  35. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  36. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68
  37. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  38. 2018Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Cloudscited by 62

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 13; 2023: 24; 2024: 19; 2025: 20; 2026: 8.

84 papers.

Sort:

By area:

  1. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  2. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  3. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
  4. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  5. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 113
  6. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  7. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  8. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 57
  9. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 53
  10. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  11. 2023Self-positioning Point-based Transformer for Point Cloud Understandingcited by 40
  12. 2023GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Trainingcited by 38
38 more
  1. 2023Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Modelscited by 25
  2. 2023Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlookcited by 24
  3. 2022PointVector: A Vector Representation In Point Cloud Analysiscited by 21
  4. 2022FBNet: Feedback Network for Point Cloud Completioncited by 20
  5. 2024Parameter-efficient Prompt Learning for 3D Point Cloud Understandingcited by 16
  6. 2022Masked Surfel Prediction for Self-Supervised Point Cloud Learningcited by 15
  7. 2023Joint Representation Learning for Text and 3D Point Cloudcited by 14
  8. 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learningcited by 14
  9. 2023Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representationcited by 12
  10. 2024GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understandingcited by 12
  11. 2024X-3D: Explicit 3D Structure Modeling for Point Cloud Recognitioncited by 11
  12. 2022PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognitioncited by 10
  13. 2025Instant4D: 4D Gaussian Splatting in Minutescited by 10
  14. 2024ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Imagescited by 9
  15. 2022GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modelingcited by 8
  16. 2022Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understandingcited by 6
  17. 2022Learning Point-Language Hierarchical Alignment for 3D Visual Groundingcited by 6
  18. 2023Region-Enhanced Feature Learning for Scene Semantic Segmentationcited by 6
  19. 2023Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentationcited by 6
  20. 2024A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)cited by 6
  21. 2024Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detectioncited by 6
  22. 2024Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysiscited by 6
  23. 2023Full Point Encoding for Local Feature Aggregation in 3D Point Cloudscited by 5
  24. 2024PointGL: A Simple Global-Local Framework for Efficient Point Cloud Analysiscited by 5
  25. 2023Synthetic Data Generation and Deep Learning for the Topological Analysis of 3D Datacited by 4
  26. 2024Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformerscited by 4
  27. 2025Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributescited by 4
  28. 2026BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generationcited by 4
  29. 2022PointNorm: Dual Normalization is All You Need for Point Cloud Analysiscited by 3
  30. 2023SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentationcited by 3
  31. 2023GAM : Gradient Attention Module of Optimization for Point Clouds Analysiscited by 3
  32. 2023GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentationcited by 3
  33. 2023EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization @Ego4D challenge 2023cited by 3
  34. 2024PointMT: Efficient Point Cloud Analysis with Hybrid MLP-Transformer Architecturecited by 3
  35. 2023Point Cloud Semantic Segmentationcited by 2
  36. 2024LoGDesc: Local geometric features aggregation for robust point cloud registrationcited by 2
  37. 2025PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentationcited by 2
  38. 2025GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detectioncited by 2

50 most cited of 84 All 84 (JSON)