mlsanityData to 14 Oct 2026

Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding

arXiv 2111.15363 ↗First posted 30 Nov 2021cs.CV cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Multi-view projection methods have demonstrated promising performance on 3D understanding tasks like 3D classification and segmentation. However, it remains unclear how to combine such multi-view methods with the widely available 3D point clouds. Previous methods use unlearned heuristics to combine features at the point level. To this end, we introduce the concept of the multi-view point cloud (Voint cloud), representing each 3D point as a set of features extracted from several view-points. This novel 3D Voint cloud representation combines the compactness of 3D point cloud representation with the natural view-awareness of multi-view representation. Naturally, we can equip this new representation with convolutional and pooling operations. We deploy a Voint neural network (VointNet) to learn representations in the Voint space. Our novel representation achieves sota performance on 3D classification, shape retrieval, and robust 3D part segmentation on standard benchmarks ( ScanObjectNN, ShapeNet Core55, and ShapeNet Parts).

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 58 of its 78 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

58 of 78 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  9. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  12. 2020Point Transformercited by 1,470
38 more
  1. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  2. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  3. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  5. 2016Group Equivariant Convolutional Networkscited by 1,165
  6. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  7. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  8. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  11. 2020PCT: Point cloud transformercited by 732
  12. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  13. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  14. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  15. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  16. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  17. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  18. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  19. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  20. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  21. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
  22. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 217
  23. 2021Group-Free 3D Object Detection via Transformerscited by 215
  24. 2019CvxNet: Learnable Convex Decompositioncited by 174
  25. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  26. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  27. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 169
  28. 2019Point-Based Multi-View Stereo Networkcited by 147
  29. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  30. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  31. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  32. 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
  33. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  34. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  35. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  36. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  37. 2019Multi-view PointNet for 3D Scene Understandingcited by 76
  38. 2018Triplet-Center Loss for Multi-View 3D Object Retrievalcited by 69

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 7; 2024: 6; 2025: 2; 2026: 2.

22 papers.

Sort:

By area:

  1. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 225
  2. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 137
  3. 2022UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Groundingcited by 69
  4. 2022EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queriescited by 25
  5. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  6. 2023Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-trainingcited by 18
  7. 2022SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Imagescited by 17
  8. 2025MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentationcited by 16
  9. 2023Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognitioncited by 13
  10. 2024TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Trackscited by 12
  11. 2022MVTN: Learning Multi-View Transformations for 3D Understandingcited by 7
  12. 2022Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understandingcited by 6
10 more
  1. 2024X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Modelscited by 5
  2. 2025UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentationcited by 4
  3. 2023Multi-View Representation is What You Need for Point-Cloud Pre-Trainingcited by 3
  4. 2023Dynamic Clustering Transformer Network for Point Cloud Segmentationcited by 2
  5. 2023Point Cloud Self-supervised Learning via 3D to Multi-view Masked Learnercited by 2
  6. 2024VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understandingcited by 2
  7. 2026CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretrainingcited by 2
  8. 2026ReMAP-DP: Reprojected Multi-view Aligned PointMaps for Diffusion Policycited by 2
  9. 2024An Optimization Framework to Enforce Multi-View Consistency for Texturing 3D Meshescited by 0
  10. 2024Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformerscited by 0